{ "id": "glm53-full-tp4-exl3", "title": "Full GLM-5.3 on Four Sparks: Cache Layout, Speed and Fidelity", "kind": "benchmark", "source_type": "community_operator_report", "summary": "Audit the 753B non-Flash EXL3 TP4 recipe, replicated and shared Q5 cache, million-token retrieval, BF16-reference fidelity and later RDMA fixes.", "runtime": "TensorFold 0.6.0 + glm-dsa-tp4 branch", "runtime_topics": [ "TensorFold" ], "hardware_topics": [ "spark", "nvidia" ], "platform_topics": [ "linux" ], "model_label": "GLM-5.3 full 753B", "model_family": "GLM", "model_id": "bertholomus/GLM-5.3-EXL3-3.0bpw", "model_release_date": null, "model_artifact": { "id": "bertholomus/GLM-5.3-EXL3-3.0bpw", "revision": null }, "evidence_state": "source_reported", "site_reproduced": false, "record_type": "curated_reference", "performance_ranking_allowed": false, "metrics": null, "metrics_status": "site_metrics_unmeasured; attributed_source_figures_in_editorial.reported_results", "conditions": { "model_revision": null, "weight_hash": null, "runtime_execution_revision": null, "input_tokens": null, "output_tokens": null, "concurrency": null, "cache_state": null, "quantization": null, "speculative_decoding": null, "temperature": null, "top_p": null }, "reported_setup": { "system": "four DGX Spark GB10, 128 GB unified memory each, direct dual-port 200G RoCE", "node_count": 4, "parallelism": "TP4", "kv_dtype": "Q5 MLA latent cache; FP8 indexer", "context_limit_tokens": 65536, "experiment_date": "2026-10-04" }, "test_profiles": [ { "label": "replicated Q5 four code streams", "evidence_url": "https://github.com/bertholomus/glm-5.3-tensorfold-tp4-4xgb10/blob/9a5c1100c68cd8ea832803c120ee63313049fc21/README.md#L57", "conditions": { "model": "GLM-5.3 (full 753B, not Flash)", "model_artifact": "bertholomus/GLM-5.3-EXL3-3.0bpw", "model_revision": null, "engine": "TensorFold 0.6.0 + glm-dsa-tp4 branch", "runtime_execution_revision": null, "measured_runtime_short": "3eb35dd", "later_branch_head_short": "ddfad35", "executed_image_digest": null, "system": "four DGX Spark GB10, 128 GB unified memory each, direct dual-port 200G RoCE", "node_count": 4, "parallelism": "TP4", "weight_precision": "EXL3 3.04 bpw whole-model average; exllamav3 1.5.3", "kv_dtype": "Q5 MLA latent cache; FP8 indexer", "draft": "native MTP-3", "vision": false, "DFlash": false, "experiment_date": "2026-10-04", "temperature": 0, "thinking": null, "input_tokens": null, "output_tokens": null, "host_peak_RAM": null, "repetitions": null, "concurrency": 4, "context_limit_tokens": 65536, "cache_state": "replicated", "metric_denominator": "source reports HTTP prompt time included; release concurrent raw usage/harness not retained", "token_accounting_verified": false, "available_serial_stream_probe_counts_nonempty_SSE_chunks": true, "release_was_computed_by_that_probe": null, "value_is_approximate": false } }, { "label": "DCP4 shared Q5 four code streams", "evidence_url": "https://github.com/bertholomus/glm-5.3-tensorfold-tp4-4xgb10/blob/9a5c1100c68cd8ea832803c120ee63313049fc21/README.md#L68", "conditions": { "model": "GLM-5.3 (full 753B, not Flash)", "model_artifact": "bertholomus/GLM-5.3-EXL3-3.0bpw", "model_revision": null, "engine": "TensorFold 0.6.0 + glm-dsa-tp4 branch", "runtime_execution_revision": null, "measured_runtime_short": "3eb35dd", "later_branch_head_short": "ddfad35", "executed_image_digest": null, "system": "four DGX Spark GB10, 128 GB unified memory each, direct dual-port 200G RoCE", "node_count": 4, "parallelism": "TP4", "weight_precision": "EXL3 3.04 bpw whole-model average; exllamav3 1.5.3", "kv_dtype": "Q5 MLA latent cache; FP8 indexer", "draft": "native MTP-3", "vision": false, "DFlash": false, "experiment_date": "2026-10-04", "temperature": 0, "thinking": null, "input_tokens": null, "output_tokens": null, "host_peak_RAM": null, "repetitions": null, "concurrency": 4, "context_limit_tokens": 1048576, "cache_state": "four streams share one DCP4 pool", "metric_denominator": "source reports HTTP prompt time included; release concurrent raw usage/harness not retained", "token_accounting_verified": false, "available_serial_stream_probe_counts_nonempty_SSE_chunks": true, "release_was_computed_by_that_probe": null, "value_is_approximate": true } }, { "label": "32K-labelled prefill", "evidence_url": "https://github.com/bertholomus/glm-5.3-tensorfold-tp4-4xgb10/blob/9a5c1100c68cd8ea832803c120ee63313049fc21/README.md#L71", "conditions": { "model": "GLM-5.3 (full 753B, not Flash)", "model_artifact": "bertholomus/GLM-5.3-EXL3-3.0bpw", "model_revision": null, "engine": "TensorFold 0.6.0 + glm-dsa-tp4 branch", "runtime_execution_revision": null, "measured_runtime_short": "3eb35dd", "later_branch_head_short": "ddfad35", "executed_image_digest": null, "system": "four DGX Spark GB10, 128 GB unified memory each, direct dual-port 200G RoCE", "node_count": 4, "parallelism": "TP4", "weight_precision": "EXL3 3.04 bpw whole-model average; exllamav3 1.5.3", "kv_dtype": "Q5 MLA latent cache; FP8 indexer", "draft": "native MTP-3", "vision": false, "DFlash": false, "experiment_date": "2026-10-04", "temperature": 0, "thinking": null, "input_tokens": null, "output_tokens": null, "host_peak_RAM": null, "repetitions": null, "concurrency": 1, "input_length_source_label": "32K", "context_limit_tokens": 1048576, "cache_state": null, "metric_denominator": "source HTTP prefill measurement, exact prompt count unreported" } }, { "label": "forward KL", "evidence_url": "https://github.com/bertholomus/glm-5.3-tensorfold-tp4-4xgb10/blob/9a5c1100c68cd8ea832803c120ee63313049fc21/README.md#L167", "conditions": { "model": "GLM-5.3 (full 753B, not Flash)", "model_artifact": "bertholomus/GLM-5.3-EXL3-3.0bpw", "model_revision": null, "engine": "TensorFold 0.6.0 + glm-dsa-tp4 branch", "runtime_execution_revision": null, "measured_runtime_short": "3eb35dd", "later_branch_head_short": "ddfad35", "executed_image_digest": null, "system": "four DGX Spark GB10, 128 GB unified memory each, direct dual-port 200G RoCE", "node_count": 4, "parallelism": "TP4", "weight_precision": "EXL3 3.04 bpw whole-model average; exllamav3 1.5.3", "kv_dtype": "no cache quantization", "draft": "native MTP-3", "vision": false, "DFlash": false, "experiment_date": null, "temperature": 0, "thinking": null, "input_tokens": null, "output_tokens": null, "host_peak_RAM": null, "repetitions": null, "concurrency": null, "quality_panel": "wikitext-2 test, 32 x 2048 = 65536 positions", "activation_dtype": "BF16", "reference": "BF16 full model", "cache_state": null, "quality_is_task_accuracy": false, "quality_arm": "forward KL" } }, { "label": "reverse KL", "evidence_url": "https://github.com/bertholomus/glm-5.3-tensorfold-tp4-4xgb10/blob/9a5c1100c68cd8ea832803c120ee63313049fc21/README.md#L168", "conditions": { "model": "GLM-5.3 (full 753B, not Flash)", "model_artifact": "bertholomus/GLM-5.3-EXL3-3.0bpw", "model_revision": null, "engine": "TensorFold 0.6.0 + glm-dsa-tp4 branch", "runtime_execution_revision": null, "measured_runtime_short": "3eb35dd", "later_branch_head_short": "ddfad35", "executed_image_digest": null, "system": "four DGX Spark GB10, 128 GB unified memory each, direct dual-port 200G RoCE", "node_count": 4, "parallelism": "TP4", "weight_precision": "EXL3 3.04 bpw whole-model average; exllamav3 1.5.3", "kv_dtype": "no cache quantization", "draft": "native MTP-3", "vision": false, "DFlash": false, "experiment_date": null, "temperature": 0, "thinking": null, "input_tokens": null, "output_tokens": null, "host_peak_RAM": null, "repetitions": null, "concurrency": null, "quality_panel": "wikitext-2 test, 32 x 2048 = 65536 positions", "activation_dtype": "BF16", "reference": "BF16 full model", "cache_state": null, "quality_is_task_accuracy": false, "quality_arm": "reverse KL" } }, { "label": "top-1 agreement", "evidence_url": "https://github.com/bertholomus/glm-5.3-tensorfold-tp4-4xgb10/blob/9a5c1100c68cd8ea832803c120ee63313049fc21/README.md#L169", "conditions": { "model": "GLM-5.3 (full 753B, not Flash)", "model_artifact": "bertholomus/GLM-5.3-EXL3-3.0bpw", "model_revision": null, "engine": "TensorFold 0.6.0 + glm-dsa-tp4 branch", "runtime_execution_revision": null, "measured_runtime_short": "3eb35dd", "later_branch_head_short": "ddfad35", "executed_image_digest": null, "system": "four DGX Spark GB10, 128 GB unified memory each, direct dual-port 200G RoCE", "node_count": 4, "parallelism": "TP4", "weight_precision": "EXL3 3.04 bpw whole-model average; exllamav3 1.5.3", "kv_dtype": "no cache quantization", "draft": "native MTP-3", "vision": false, "DFlash": false, "experiment_date": null, "temperature": 0, "thinking": null, "input_tokens": null, "output_tokens": null, "host_peak_RAM": null, "repetitions": null, "concurrency": null, "quality_panel": "wikitext-2 test, 32 x 2048 = 65536 positions", "activation_dtype": "BF16", "reference": "BF16 full model", "cache_state": null, "quality_is_task_accuracy": false, "quality_arm": "top-1 agreement" } }, { "label": "quant perplexity", "evidence_url": "https://github.com/bertholomus/glm-5.3-tensorfold-tp4-4xgb10/blob/9a5c1100c68cd8ea832803c120ee63313049fc21/README.md#L170", "conditions": { "model": "GLM-5.3 (full 753B, not Flash)", "model_artifact": "bertholomus/GLM-5.3-EXL3-3.0bpw", "model_revision": null, "engine": "TensorFold 0.6.0 + glm-dsa-tp4 branch", "runtime_execution_revision": null, "measured_runtime_short": "3eb35dd", "later_branch_head_short": "ddfad35", "executed_image_digest": null, "system": "four DGX Spark GB10, 128 GB unified memory each, direct dual-port 200G RoCE", "node_count": 4, "parallelism": "TP4", "weight_precision": "EXL3 3.04 bpw whole-model average; exllamav3 1.5.3", "kv_dtype": "no cache quantization", "draft": "native MTP-3", "vision": false, "DFlash": false, "experiment_date": null, "temperature": 0, "thinking": null, "input_tokens": null, "output_tokens": null, "host_peak_RAM": null, "repetitions": null, "concurrency": null, "quality_panel": "wikitext-2 test, 32 x 2048 = 65536 positions", "activation_dtype": "BF16", "reference": "BF16 full model", "cache_state": null, "quality_is_task_accuracy": false, "quality_arm": "quant perplexity" } }, { "label": "BF16 perplexity", "evidence_url": "https://github.com/bertholomus/glm-5.3-tensorfold-tp4-4xgb10/blob/9a5c1100c68cd8ea832803c120ee63313049fc21/README.md#L170", "conditions": { "model": "GLM-5.3 (full 753B, not Flash)", "model_artifact": "bertholomus/GLM-5.3-EXL3-3.0bpw", "model_revision": null, "engine": "TensorFold 0.6.0 + glm-dsa-tp4 branch", "runtime_execution_revision": null, "measured_runtime_short": "3eb35dd", "later_branch_head_short": "ddfad35", "executed_image_digest": null, "system": "four DGX Spark GB10, 128 GB unified memory each, direct dual-port 200G RoCE", "node_count": 4, "parallelism": "TP4", "weight_precision": "EXL3 3.04 bpw whole-model average; exllamav3 1.5.3", "kv_dtype": "no cache quantization", "draft": "native MTP-3", "vision": false, "DFlash": false, "experiment_date": null, "temperature": 0, "thinking": null, "input_tokens": null, "output_tokens": null, "host_peak_RAM": null, "repetitions": null, "concurrency": null, "quality_panel": "wikitext-2 test, 32 x 2048 = 65536 positions", "activation_dtype": "BF16", "reference": "BF16 full model", "cache_state": null, "quality_is_task_accuracy": false, "quality_arm": "BF16 perplexity" } }, { "label": "served engine prompt-path KL", "evidence_url": "https://github.com/bertholomus/glm-5.3-tensorfold-tp4-4xgb10/blob/9a5c1100c68cd8ea832803c120ee63313049fc21/README.md#L173", "conditions": { "model": "GLM-5.3 (full 753B, not Flash)", "model_artifact": "bertholomus/GLM-5.3-EXL3-3.0bpw", "model_revision": null, "engine": "TensorFold 0.6.0 + glm-dsa-tp4 branch", "runtime_execution_revision": null, "measured_runtime_short": "3eb35dd", "later_branch_head_short": "ddfad35", "executed_image_digest": null, "system": "four DGX Spark GB10, 128 GB unified memory each, direct dual-port 200G RoCE", "node_count": 4, "parallelism": "TP4", "weight_precision": "EXL3 3.04 bpw whole-model average; exllamav3 1.5.3", "kv_dtype": "served path; panel-specific cache details not retained", "draft": "native MTP-3", "vision": false, "DFlash": false, "experiment_date": null, "temperature": 0, "thinking": null, "input_tokens": null, "output_tokens": null, "host_peak_RAM": null, "repetitions": null, "concurrency": null, "quality_panel": "wikitext-2 test, 32 x 2048 = 65536 positions", "activation_dtype": "BF16", "reference": "BF16 full model", "cache_state": null, "quality_is_task_accuracy": false, "quality_arm": "served engine" } } ], "deployment_options": [], "recipe_parameters": null, "measurement_scope": "original_reported_performance_quality_and_failure_cases", "notes": [ "Selected values are source excerpts, not independent experiment counts." ], "limitations": [ "No independent Run AI Here model test.", "Read source date, exact execution identity, denominator, memory scope and retries per observation.", "No unmatched quality ranking or hardware speed ranking." ], "comparison_status": "not_comparable", "editorial_status": "source_derived_detailed_article", "public_benchmark_snapshot": false, "source": { "publisher": "bertholomus", "repository": "bertholomus/glm-5.3-tensorfold-tp4-4xgb10", "platform": "github", "revision": "9a5c1100c68cd8ea832803c120ee63313049fc21", "document_path": "README.md", "pinned_url": "https://github.com/bertholomus/glm-5.3-tensorfold-tp4-4xgb10/blob/9a5c1100c68cd8ea832803c120ee63313049fc21/README.md", "document_sha256": "088db2d55fbb6aecc2cc6576b3db9a26e70a13a2b5d89b83ad1cb0b54b03a6b4", "last_commit_at": "2026-10-09T05:31:45Z", "url": "https://github.com/bertholomus/glm-5.3-tensorfold-tp4-4xgb10", "report_url": "https://github.com/bertholomus/glm-5.3-tensorfold-tp4-4xgb10/blob/9a5c1100c68cd8ea832803c120ee63313049fc21/README.md", "checked_on": "2026-10-18", "metadata_status": "checked" }, "supplemental_sources": [ { "document_id": "glmfull-speed-method", "parent_record_id": "glm53-full-tp4-exl3", "publisher": "bertholomus", "repository": "bertholomus/glm-5.3-tensorfold-tp4-4xgb10", "revision": "9a5c1100c68cd8ea832803c120ee63313049fc21", "document_path": "bench/tf_bench.py", "pinned_url": "https://github.com/bertholomus/glm-5.3-tensorfold-tp4-4xgb10/blob/9a5c1100c68cd8ea832803c120ee63313049fc21/bench/tf_bench.py", "document_sha256": "9652bf8a7359414ad451dc05ceee4f4bef6cfcf489e65334e9bec1e7895192b2", "last_commit_at": "2026-10-09T05:31:45Z", "checked_on": "2026-10-18", "public_URL_is_immutable": true, "revision_kind": "Git source document revision; executed engine and weight revisions are separate fields" }, { "document_id": "glmfull-needle-method", "parent_record_id": "glm53-full-tp4-exl3", "publisher": "bertholomus", "repository": "bertholomus/glm-5.3-tensorfold-tp4-4xgb10", "revision": "9a5c1100c68cd8ea832803c120ee63313049fc21", "document_path": "bench/tf_needle.py", "pinned_url": "https://github.com/bertholomus/glm-5.3-tensorfold-tp4-4xgb10/blob/9a5c1100c68cd8ea832803c120ee63313049fc21/bench/tf_needle.py", "document_sha256": "cdf8ab15fc7ec88073a714696b561f2e7a292ac9a0490571935bbe2cc933a4ab", "last_commit_at": "2026-10-09T05:31:45Z", "checked_on": "2026-10-18", "public_URL_is_immutable": true, "revision_kind": "Git source document revision; executed engine and weight revisions are separate fields" }, { "document_id": "glmfull-greedy-method", "parent_record_id": "glm53-full-tp4-exl3", "publisher": "bertholomus", "repository": "bertholomus/glm-5.3-tensorfold-tp4-4xgb10", "revision": "9a5c1100c68cd8ea832803c120ee63313049fc21", "document_path": "bench/tf_greedy.py", "pinned_url": "https://github.com/bertholomus/glm-5.3-tensorfold-tp4-4xgb10/blob/9a5c1100c68cd8ea832803c120ee63313049fc21/bench/tf_greedy.py", "document_sha256": "834c9f1e73af9431b585adf00aa3f14254d8713b638a4fa95c36b6a2074dbf37", "last_commit_at": "2026-10-09T05:31:45Z", "checked_on": "2026-10-18", "public_URL_is_immutable": true, "revision_kind": "Git source document revision; executed engine and weight revisions are separate fields" } ], "license": { "declared_spdx": null, "scope": "Attribution and finite original factual interpretation only; models and dependencies retain their own terms." }, "editorial": { "version": 1, "published_on": "2026-10-18", "modified_on": "2026-10-18", "byline": "Run AI Here editorial", "creation_method": "Local Spark Qwen draft; Codex source audit and rewrite. No site model benchmark.", "answer": "The source runs full GLM-5.3 on four GB10 nodes with EXL3 and native MTP-3. Its two cache layouts trade reported aggregate code throughput for a larger shared window. Peak RAM and a task-accuracy suite are absent; the published quality panel measures quantization fidelity.", "sections": [ { "heading": "What must the deployment provide?", "paragraphs": [ "Four 128 GB GB10 nodes use TP4, direct dual-port 200G RoCE, TensorFold 0.6.0 plus the model branch, EXL3 average 3.04 bpw and native MTP-3. It is text-only and does not use DFlash. The approximately 69.86 GiB per-rank weight fit is shape-derived and excludes whole-run cache and working memory." ], "citations": [ "https://github.com/bertholomus/glm-5.3-tensorfold-tp4-4xgb10/blob/9a5c1100c68cd8ea832803c120ee63313049fc21/README.md" ] }, { "heading": "Which release produced the speed table?", "paragraphs": [ "October 4 release numbers are attributed to engine prefix 3eb35dd; the later head ddfad35 adds per-device RDMA completion matching and graph prewarm. The full executed commit and checkpoint revision are unreported. Replicated Q5 at 65536/stream reports 82 aggregate code tokens/s for four streams; shared DCP4 Q5 at a 1048576-token pool reports about 64." ], "citations": [ "https://github.com/bertholomus/glm-5.3-tensorfold-tp4-4xgb10/blob/9a5c1100c68cd8ea832803c120ee63313049fc21/README.md" ] }, { "heading": "How are HTTP accounting and fidelity limited?", "paragraphs": [ "The README calls the rates HTTP measurements with prompt time included. Its available serial streaming probe counts nonempty SSE chunks rather than verified tokenizer/usage tokens, while the exact concurrent release harness/raw accounting is not retained here. The fidelity panel uses BF16 activations and no cache quantization, with forward KL 0.109, reverse KL 0.123 and 90.2 percent top-1 agreement. It is not a task-accuracy test." ], "citations": [ "https://github.com/bertholomus/glm-5.3-tensorfold-tp4-4xgb10/blob/9a5c1100c68cd8ea832803c120ee63313049fc21/README.md", "https://github.com/bertholomus/glm-5.3-tensorfold-tp4-4xgb10/blob/9a5c1100c68cd8ea832803c120ee63313049fc21/bench/tf_bench.py", "https://github.com/bertholomus/glm-5.3-tensorfold-tp4-4xgb10/blob/9a5c1100c68cd8ea832803c120ee63313049fc21/bench/tf_greedy.py" ] }, { "heading": "What does the long-window result establish?", "paragraphs": [ "The source finds a needle at 1039064 actual input tokens, reports 402 tokens/s at nominal 32K and about 76s first-token latency near 31K. Those do not demonstrate four full-million-token requests running together. Repetition counts, long-input peak RAM and raw per-request release accounting remain missing." ], "citations": [ "https://github.com/bertholomus/glm-5.3-tensorfold-tp4-4xgb10/blob/9a5c1100c68cd8ea832803c120ee63313049fc21/README.md", "https://github.com/bertholomus/glm-5.3-tensorfold-tp4-4xgb10/blob/9a5c1100c68cd8ea832803c120ee63313049fc21/bench/tf_needle.py" ] } ], "facts": [], "reported_results": [ { "label": "replicated Q5 four code streams", "metric": "aggregate_output_rate", "value": 82, "unit": "tokens/s", "statistic": "source-reported observation; dispersion unreported", "uncertainty": null, "conditions": { "model": "GLM-5.3 (full 753B, not Flash)", "model_artifact": "bertholomus/GLM-5.3-EXL3-3.0bpw", "model_revision": null, "engine": "TensorFold 0.6.0 + glm-dsa-tp4 branch", "runtime_execution_revision": null, "measured_runtime_short": "3eb35dd", "later_branch_head_short": "ddfad35", "executed_image_digest": null, "system": "four DGX Spark GB10, 128 GB unified memory each, direct dual-port 200G RoCE", "node_count": 4, "parallelism": "TP4", "weight_precision": "EXL3 3.04 bpw whole-model average; exllamav3 1.5.3", "kv_dtype": "Q5 MLA latent cache; FP8 indexer", "draft": "native MTP-3", "vision": false, "DFlash": false, "experiment_date": "2026-10-04", "temperature": 0, "thinking": null, "input_tokens": null, "output_tokens": null, "host_peak_RAM": null, "repetitions": null, "concurrency": 4, "context_limit_tokens": 65536, "cache_state": "replicated", "metric_denominator": "source reports HTTP prompt time included; release concurrent raw usage/harness not retained", "token_accounting_verified": false, "available_serial_stream_probe_counts_nonempty_SSE_chunks": true, "release_was_computed_by_that_probe": null, "value_is_approximate": false }, "evidence_state": "source_reported", "site_reproduced": false, "source_document_id": "glmfull-tp4-readme", "source_document_sha256": "088db2d55fbb6aecc2cc6576b3db9a26e70a13a2b5d89b83ad1cb0b54b03a6b4", "source_line": 57, "evidence_url": "https://github.com/bertholomus/glm-5.3-tensorfold-tp4-4xgb10/blob/9a5c1100c68cd8ea832803c120ee63313049fc21/README.md#L57" }, { "label": "DCP4 shared Q5 four code streams", "metric": "aggregate_output_rate", "value": 64, "unit": "tokens/s", "statistic": "source-reported observation; dispersion unreported", "uncertainty": null, "conditions": { "model": "GLM-5.3 (full 753B, not Flash)", "model_artifact": "bertholomus/GLM-5.3-EXL3-3.0bpw", "model_revision": null, "engine": "TensorFold 0.6.0 + glm-dsa-tp4 branch", "runtime_execution_revision": null, "measured_runtime_short": "3eb35dd", "later_branch_head_short": "ddfad35", "executed_image_digest": null, "system": "four DGX Spark GB10, 128 GB unified memory each, direct dual-port 200G RoCE", "node_count": 4, "parallelism": "TP4", "weight_precision": "EXL3 3.04 bpw whole-model average; exllamav3 1.5.3", "kv_dtype": "Q5 MLA latent cache; FP8 indexer", "draft": "native MTP-3", "vision": false, "DFlash": false, "experiment_date": "2026-10-04", "temperature": 0, "thinking": null, "input_tokens": null, "output_tokens": null, "host_peak_RAM": null, "repetitions": null, "concurrency": 4, "context_limit_tokens": 1048576, "cache_state": "four streams share one DCP4 pool", "metric_denominator": "source reports HTTP prompt time included; release concurrent raw usage/harness not retained", "token_accounting_verified": false, "available_serial_stream_probe_counts_nonempty_SSE_chunks": true, "release_was_computed_by_that_probe": null, "value_is_approximate": true }, "evidence_state": "source_reported", "site_reproduced": false, "source_document_id": "glmfull-tp4-readme", "source_document_sha256": "088db2d55fbb6aecc2cc6576b3db9a26e70a13a2b5d89b83ad1cb0b54b03a6b4", "source_line": 68, "evidence_url": "https://github.com/bertholomus/glm-5.3-tensorfold-tp4-4xgb10/blob/9a5c1100c68cd8ea832803c120ee63313049fc21/README.md#L68" }, { "label": "32K-labelled prefill", "metric": "prefill_rate", "value": 402, "unit": "tokens/s", "statistic": "source-reported observation; dispersion unreported", "uncertainty": null, "conditions": { "model": "GLM-5.3 (full 753B, not Flash)", "model_artifact": "bertholomus/GLM-5.3-EXL3-3.0bpw", "model_revision": null, "engine": "TensorFold 0.6.0 + glm-dsa-tp4 branch", "runtime_execution_revision": null, "measured_runtime_short": "3eb35dd", "later_branch_head_short": "ddfad35", "executed_image_digest": null, "system": "four DGX Spark GB10, 128 GB unified memory each, direct dual-port 200G RoCE", "node_count": 4, "parallelism": "TP4", "weight_precision": "EXL3 3.04 bpw whole-model average; exllamav3 1.5.3", "kv_dtype": "Q5 MLA latent cache; FP8 indexer", "draft": "native MTP-3", "vision": false, "DFlash": false, "experiment_date": "2026-10-04", "temperature": 0, "thinking": null, "input_tokens": null, "output_tokens": null, "host_peak_RAM": null, "repetitions": null, "concurrency": 1, "input_length_source_label": "32K", "context_limit_tokens": 1048576, "cache_state": null, "metric_denominator": "source HTTP prefill measurement, exact prompt count unreported" }, "evidence_state": "source_reported", "site_reproduced": false, "source_document_id": "glmfull-tp4-readme", "source_document_sha256": "088db2d55fbb6aecc2cc6576b3db9a26e70a13a2b5d89b83ad1cb0b54b03a6b4", "source_line": 71, "evidence_url": "https://github.com/bertholomus/glm-5.3-tensorfold-tp4-4xgb10/blob/9a5c1100c68cd8ea832803c120ee63313049fc21/README.md#L71" }, { "label": "forward KL", "metric": "KL_reference_to_quant", "value": 0.109, "unit": "nats", "statistic": "source-reported observation; dispersion unreported", "uncertainty": null, "conditions": { "model": "GLM-5.3 (full 753B, not Flash)", "model_artifact": "bertholomus/GLM-5.3-EXL3-3.0bpw", "model_revision": null, "engine": "TensorFold 0.6.0 + glm-dsa-tp4 branch", "runtime_execution_revision": null, "measured_runtime_short": "3eb35dd", "later_branch_head_short": "ddfad35", "executed_image_digest": null, "system": "four DGX Spark GB10, 128 GB unified memory each, direct dual-port 200G RoCE", "node_count": 4, "parallelism": "TP4", "weight_precision": "EXL3 3.04 bpw whole-model average; exllamav3 1.5.3", "kv_dtype": "no cache quantization", "draft": "native MTP-3", "vision": false, "DFlash": false, "experiment_date": null, "temperature": 0, "thinking": null, "input_tokens": null, "output_tokens": null, "host_peak_RAM": null, "repetitions": null, "concurrency": null, "quality_panel": "wikitext-2 test, 32 x 2048 = 65536 positions", "activation_dtype": "BF16", "reference": "BF16 full model", "cache_state": null, "quality_is_task_accuracy": false, "quality_arm": "forward KL" }, "evidence_state": "source_reported", "site_reproduced": false, "source_document_id": "glmfull-tp4-readme", "source_document_sha256": "088db2d55fbb6aecc2cc6576b3db9a26e70a13a2b5d89b83ad1cb0b54b03a6b4", "source_line": 167, "evidence_url": "https://github.com/bertholomus/glm-5.3-tensorfold-tp4-4xgb10/blob/9a5c1100c68cd8ea832803c120ee63313049fc21/README.md#L167" }, { "label": "reverse KL", "metric": "KL_quant_to_reference", "value": 0.123, "unit": "nats", "statistic": "source-reported observation; dispersion unreported", "uncertainty": null, "conditions": { "model": "GLM-5.3 (full 753B, not Flash)", "model_artifact": "bertholomus/GLM-5.3-EXL3-3.0bpw", "model_revision": null, "engine": "TensorFold 0.6.0 + glm-dsa-tp4 branch", "runtime_execution_revision": null, "measured_runtime_short": "3eb35dd", "later_branch_head_short": "ddfad35", "executed_image_digest": null, "system": "four DGX Spark GB10, 128 GB unified memory each, direct dual-port 200G RoCE", "node_count": 4, "parallelism": "TP4", "weight_precision": "EXL3 3.04 bpw whole-model average; exllamav3 1.5.3", "kv_dtype": "no cache quantization", "draft": "native MTP-3", "vision": false, "DFlash": false, "experiment_date": null, "temperature": 0, "thinking": null, "input_tokens": null, "output_tokens": null, "host_peak_RAM": null, "repetitions": null, "concurrency": null, "quality_panel": "wikitext-2 test, 32 x 2048 = 65536 positions", "activation_dtype": "BF16", "reference": "BF16 full model", "cache_state": null, "quality_is_task_accuracy": false, "quality_arm": "reverse KL" }, "evidence_state": "source_reported", "site_reproduced": false, "source_document_id": "glmfull-tp4-readme", "source_document_sha256": "088db2d55fbb6aecc2cc6576b3db9a26e70a13a2b5d89b83ad1cb0b54b03a6b4", "source_line": 168, "evidence_url": "https://github.com/bertholomus/glm-5.3-tensorfold-tp4-4xgb10/blob/9a5c1100c68cd8ea832803c120ee63313049fc21/README.md#L168" }, { "label": "top-1 agreement", "metric": "top1_agreement", "value": 90.2, "unit": "percent", "statistic": "source-reported observation; dispersion unreported", "uncertainty": null, "conditions": { "model": "GLM-5.3 (full 753B, not Flash)", "model_artifact": "bertholomus/GLM-5.3-EXL3-3.0bpw", "model_revision": null, "engine": "TensorFold 0.6.0 + glm-dsa-tp4 branch", "runtime_execution_revision": null, "measured_runtime_short": "3eb35dd", "later_branch_head_short": "ddfad35", "executed_image_digest": null, "system": "four DGX Spark GB10, 128 GB unified memory each, direct dual-port 200G RoCE", "node_count": 4, "parallelism": "TP4", "weight_precision": "EXL3 3.04 bpw whole-model average; exllamav3 1.5.3", "kv_dtype": "no cache quantization", "draft": "native MTP-3", "vision": false, "DFlash": false, "experiment_date": null, "temperature": 0, "thinking": null, "input_tokens": null, "output_tokens": null, "host_peak_RAM": null, "repetitions": null, "concurrency": null, "quality_panel": "wikitext-2 test, 32 x 2048 = 65536 positions", "activation_dtype": "BF16", "reference": "BF16 full model", "cache_state": null, "quality_is_task_accuracy": false, "quality_arm": "top-1 agreement" }, "evidence_state": "source_reported", "site_reproduced": false, "source_document_id": "glmfull-tp4-readme", "source_document_sha256": "088db2d55fbb6aecc2cc6576b3db9a26e70a13a2b5d89b83ad1cb0b54b03a6b4", "source_line": 169, "evidence_url": "https://github.com/bertholomus/glm-5.3-tensorfold-tp4-4xgb10/blob/9a5c1100c68cd8ea832803c120ee63313049fc21/README.md#L169" }, { "label": "quant perplexity", "metric": "perplexity", "value": 2.911, "unit": "perplexity", "statistic": "source-reported observation; dispersion unreported", "uncertainty": null, "conditions": { "model": "GLM-5.3 (full 753B, not Flash)", "model_artifact": "bertholomus/GLM-5.3-EXL3-3.0bpw", "model_revision": null, "engine": "TensorFold 0.6.0 + glm-dsa-tp4 branch", "runtime_execution_revision": null, "measured_runtime_short": "3eb35dd", "later_branch_head_short": "ddfad35", "executed_image_digest": null, "system": "four DGX Spark GB10, 128 GB unified memory each, direct dual-port 200G RoCE", "node_count": 4, "parallelism": "TP4", "weight_precision": "EXL3 3.04 bpw whole-model average; exllamav3 1.5.3", "kv_dtype": "no cache quantization", "draft": "native MTP-3", "vision": false, "DFlash": false, "experiment_date": null, "temperature": 0, "thinking": null, "input_tokens": null, "output_tokens": null, "host_peak_RAM": null, "repetitions": null, "concurrency": null, "quality_panel": "wikitext-2 test, 32 x 2048 = 65536 positions", "activation_dtype": "BF16", "reference": "BF16 full model", "cache_state": null, "quality_is_task_accuracy": false, "quality_arm": "quant perplexity" }, "evidence_state": "source_reported", "site_reproduced": false, "source_document_id": "glmfull-tp4-readme", "source_document_sha256": "088db2d55fbb6aecc2cc6576b3db9a26e70a13a2b5d89b83ad1cb0b54b03a6b4", "source_line": 170, "evidence_url": "https://github.com/bertholomus/glm-5.3-tensorfold-tp4-4xgb10/blob/9a5c1100c68cd8ea832803c120ee63313049fc21/README.md#L170" }, { "label": "BF16 perplexity", "metric": "perplexity", "value": 2.75, "unit": "perplexity", "statistic": "source-reported observation; dispersion unreported", "uncertainty": null, "conditions": { "model": "GLM-5.3 (full 753B, not Flash)", "model_artifact": "bertholomus/GLM-5.3-EXL3-3.0bpw", "model_revision": null, "engine": "TensorFold 0.6.0 + glm-dsa-tp4 branch", "runtime_execution_revision": null, "measured_runtime_short": "3eb35dd", "later_branch_head_short": "ddfad35", "executed_image_digest": null, "system": "four DGX Spark GB10, 128 GB unified memory each, direct dual-port 200G RoCE", "node_count": 4, "parallelism": "TP4", "weight_precision": "EXL3 3.04 bpw whole-model average; exllamav3 1.5.3", "kv_dtype": "no cache quantization", "draft": "native MTP-3", "vision": false, "DFlash": false, "experiment_date": null, "temperature": 0, "thinking": null, "input_tokens": null, "output_tokens": null, "host_peak_RAM": null, "repetitions": null, "concurrency": null, "quality_panel": "wikitext-2 test, 32 x 2048 = 65536 positions", "activation_dtype": "BF16", "reference": "BF16 full model", "cache_state": null, "quality_is_task_accuracy": false, "quality_arm": "BF16 perplexity" }, "evidence_state": "source_reported", "site_reproduced": false, "source_document_id": "glmfull-tp4-readme", "source_document_sha256": "088db2d55fbb6aecc2cc6576b3db9a26e70a13a2b5d89b83ad1cb0b54b03a6b4", "source_line": 170, "evidence_url": "https://github.com/bertholomus/glm-5.3-tensorfold-tp4-4xgb10/blob/9a5c1100c68cd8ea832803c120ee63313049fc21/README.md#L170" }, { "label": "served engine prompt-path KL", "metric": "KL_reference_to_engine", "value": 0.111, "unit": "nats", "statistic": "source-reported observation; dispersion unreported", "uncertainty": null, "conditions": { "model": "GLM-5.3 (full 753B, not Flash)", "model_artifact": "bertholomus/GLM-5.3-EXL3-3.0bpw", "model_revision": null, "engine": "TensorFold 0.6.0 + glm-dsa-tp4 branch", "runtime_execution_revision": null, "measured_runtime_short": "3eb35dd", "later_branch_head_short": "ddfad35", "executed_image_digest": null, "system": "four DGX Spark GB10, 128 GB unified memory each, direct dual-port 200G RoCE", "node_count": 4, "parallelism": "TP4", "weight_precision": "EXL3 3.04 bpw whole-model average; exllamav3 1.5.3", "kv_dtype": "served path; panel-specific cache details not retained", "draft": "native MTP-3", "vision": false, "DFlash": false, "experiment_date": null, "temperature": 0, "thinking": null, "input_tokens": null, "output_tokens": null, "host_peak_RAM": null, "repetitions": null, "concurrency": null, "quality_panel": "wikitext-2 test, 32 x 2048 = 65536 positions", "activation_dtype": "BF16", "reference": "BF16 full model", "cache_state": null, "quality_is_task_accuracy": false, "quality_arm": "served engine" }, "evidence_state": "source_reported", "site_reproduced": false, "source_document_id": "glmfull-tp4-readme", "source_document_sha256": "088db2d55fbb6aecc2cc6576b3db9a26e70a13a2b5d89b83ad1cb0b54b03a6b4", "source_line": 173, "evidence_url": "https://github.com/bertholomus/glm-5.3-tensorfold-tp4-4xgb10/blob/9a5c1100c68cd8ea832803c120ee63313049fc21/README.md#L173" } ], "source_document_sha256": "088db2d55fbb6aecc2cc6576b3db9a26e70a13a2b5d89b83ad1cb0b54b03a6b4" }, "case_reports": [ { "classification": "source_reported_RDMA_completion_collision", "old_error": "ibv_post_recv failed", "fix_short": "cad0d2a", "measured_release_short": "3eb35dd", "later_head_short": "ddfad35", "full_execution_revision": null, "source_document_id": "glmfull-tp4-readme", "source_document_sha256": "088db2d55fbb6aecc2cc6576b3db9a26e70a13a2b5d89b83ad1cb0b54b03a6b4", "source_line": 35, "evidence_url": "https://github.com/bertholomus/glm-5.3-tensorfold-tp4-4xgb10/blob/9a5c1100c68cd8ea832803c120ee63313049fc21/README.md#L35" } ], "quality_comparisons": [ { "panel": "32x2048 wikitext-2", "BF16_activations": true, "cache_quantization": false, "forward_KL": 0.109, "reverse_KL": 0.123, "top1_percent": 90.2, "quant_PPL": 2.911, "BF16_PPL": 2.75, "task_accuracy": null } ], "memory_observations": [ { "kind": "shape-derived weights per rank, not peak", "value": 69.86, "unit": "GiB", "is_measured_peak": false, "whole_system_peak": null, "source_document_id": "glmfull-tp4-readme", "source_document_sha256": "088db2d55fbb6aecc2cc6576b3db9a26e70a13a2b5d89b83ad1cb0b54b03a6b4", "source_line": 121, "evidence_url": "https://github.com/bertholomus/glm-5.3-tensorfold-tp4-4xgb10/blob/9a5c1100c68cd8ea832803c120ee63313049fc21/README.md#L121" } ], "long_context_cases": [ { "actual_input_tokens": 1039064, "needle_found": true, "independent_repeats": null, "concurrent_full_window_requests_proven": false, "source_document_id": "glmfull-tp4-readme", "source_document_sha256": "088db2d55fbb6aecc2cc6576b3db9a26e70a13a2b5d89b83ad1cb0b54b03a6b4", "source_line": 71, "evidence_url": "https://github.com/bertholomus/glm-5.3-tensorfold-tp4-4xgb10/blob/9a5c1100c68cd8ea832803c120ee63313049fc21/README.md#L71" } ] }