llama.cpp on Spark: Q4_K_M prefill and decode

What experiment is being described?

The report studies Qwen3 and Ministral 3 Q4_K_M artifacts on a single GB10 Spark with 128 GB unified memory. Prompt processing is tabulated at context depths 512 and 16,384; single-batch generation at 512 and 2,048. Context depth is the source table’s label, not a specified generated-output budget or a maximum capacity test.

Source: DandinPower · pinned document ↗

What is a useful concrete comparison?

The selected Qwen3 30B MoE row reports 89.3 decode tokens/s at depth 512 and 83.8 at 2,048, while the 32B dense row reports 10.7 at depth 512. These results illustrate the author’s bandwidth interpretation for this particular pair of Q4_K_M artifacts. They do not establish equal quality or the same outcome for another MoE family.

Source: DandinPower · pinned document ↗

What prevents a strong reproduction claim?

The report does not identify exact weight hashes, executed runtime commit, output lengths, cache policy or repetitions. Those gaps remain explicit. Without them, a later reader cannot know whether a discrepancy comes from kernels, artifacts or workload. A tested context depth also cannot certify the machine’s maximum context.

Source: DandinPower · pinned document ↗

How is the source reused?

This article gives a small attributed factual selection with an original explanation. Repository metadata does not declare a license, so the full result table and prose are left with the original author. No independent run is claimed, and prefill and decode remain separate measurement types.

Source: DandinPower · pinned document ↗

Reported figures and their conditions

Selected facts reported by the original author. Each row has its own configuration and measurement boundary. Run AI Here has not reproduced these tests.