# DeepSeek-V4.1-Flash-1017: official model and deployment card

The 17 October checkpoint: official weights, protocol details and minimal local inference. Start here to identify 1017 before reading a deployment recipe.

- Type: Official model card
- Evidence: source_reported; site reproduced: false
- Model family: DeepSeek
- Model: deepseek-ai/DeepSeek-V4.1-Flash-1017
- Original author: deepseek-ai
- Original project: https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash-1017
- Pinned document: https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash-1017/blob/1bae0e1088993b9b82de08f59de5be5a34e42170/README.md
- Source revision: 1bae0e1088993b9b82de08f59de5be5a34e42170
- Source commit time (not experiment date): 2026-10-17T05:46:55.000Z
- Checked: 2026-10-17
- Experiment date: None
- Runtime topics: Reference inference
- Hardware topics: 
- Reported setup: {"system": null, "node_count": null, "parallelism": null, "kv_dtype": null, "context_limit_tokens": null, "experiment_date": null}
- Performance figures: attributed selections with per-point conditions; no cross-source ranking

## Conditions

Unknown is null. Recipe options are not measured benchmark settings.

```json
{
  "conditions": {
    "model_revision": "1bae0e1088993b9b82de08f59de5be5a34e42170",
    "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
  },
  "test_profiles": [],
  "recipe_parameters": null,
  "deployment_options": []
}
```

## Reading notes

- The publisher supplies an encoder rather than a Jinja chat template.
- Minimal inference demonstrates converted per-rank weights; it is a reference implementation.
- Capability tables use named harnesses; they are not workstation speed measurements.

## Limits

- Older V4.1 community speed reports do not establish 1017 performance.
- An advertised 1M context is not a tested capacity for an arbitrary machine.

## License declaration

{"declared_spdx": "mit", "declared_name": null, "scope": "Publisher model-card declaration; inspect the linked LICENSE and artifact-specific terms."}


## Editorial answer

The 17 October checkpoint: official weights, protocol details and minimal local inference. Start here to identify 1017 before reading a deployment recipe.

By Run AI Here editorial · 2026-10-17

AI-assisted source reading and original editorial synthesis; no independent model execution.

## What changed in the 1017 checkpoint?

DeepSeek published this weight refresh on 17 October 2026. The model name includes 1017, so it identifies a different artifact from the September launch checkpoint used by the older workstation reports. Start from the pinned weight revision on this page and preserve the encoder, tokenizer and conversion identity with it. A runtime recipe that now defaults to 1017 does not retroactively update an earlier speed experiment.

Sources: https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash-1017/blob/1bae0e1088993b9b82de08f59de5be5a34e42170/README.md#L43

## How should prompts and tool calls be encoded?

The release supplies a Python encoding reference instead of a Jinja chat template. Its maintained deepseek-recipe toolkit translates API messages into the model protocol and parses responses. That toolkit does not perform inference, run tools or provide HTTP transport. A generic chat-template substitution can therefore change behavior even when the weights load successfully.

Sources: https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash-1017/blob/1bae0e1088993b9b82de08f59de5be5a34e42170/README.md#L69

## What do the capability figures establish?

The publisher reports HLE without tools as 42.6 on the full benchmark and 44.0 on its text-only subset. These populations differ. DeepSWE v1.1 uses Mini-SWE-V2, while Terminal-Bench 4.0 uses Claude Code. The figures describe the publisher’s evaluation protocol; no local GPU configuration or tokens-per-second measurement is established by that table.

Sources: https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash-1017/blob/1bae0e1088993b9b82de08f59de5be5a34e42170/README.md#L65

## Which inference settings should travel with a reproduction?

The card recommends temperature 1.0, top_p 1.0, a 1M-token context and an output budget of at least 256K tokens. These are publisher recommendations, not evidence that a particular workstation can allocate that window. The separate minimal-inference example is a reference implementation requiring conversion into per-rank weights; it is not a drop-in production server.

Sources: https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash-1017/blob/1bae0e1088993b9b82de08f59de5be5a34e42170/README.md#L77

## Attributed configuration facts

```json
[
  {
    "name": "Recommended sampling",
    "value": "temperature 1.0; top_p 1.0",
    "classification": "publisher_declaration",
    "evidence_url": "https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash-1017/blob/1bae0e1088993b9b82de08f59de5be5a34e42170/README.md#L81",
    "source_document_sha256": "b72b796e4f4c739eca5d0ad360a7679b39118ca7eb64891f7151a527b292c42a"
  },
  {
    "name": "Published context / recommended output budget",
    "value": "1M context; max_tokens at least 256K",
    "classification": "publisher_declaration",
    "evidence_url": "https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash-1017/blob/1bae0e1088993b9b82de08f59de5be5a34e42170/README.md#L84",
    "source_document_sha256": "b72b796e4f4c739eca5d0ad360a7679b39118ca7eb64891f7151a527b292c42a"
  },
  {
    "name": "Prompt interface",
    "value": "Python encoder; no Jinja-format chat template",
    "classification": "publisher_declaration",
    "evidence_url": "https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash-1017/blob/1bae0e1088993b9b82de08f59de5be5a34e42170/README.md#L69",
    "source_document_sha256": "b72b796e4f4c739eca5d0ad360a7679b39118ca7eb64891f7151a527b292c42a"
  }
]
```

## Selected source-reported figures

Each point retains its own configuration, measurement unit and source. No site reproduction or cross-source ranking.

```json
[
  {
    "label": "HLE without tools, full set",
    "metric": "HLE",
    "value": 42.6,
    "unit": "reported score",
    "statistic": "reported value",
    "uncertainty": null,
    "conditions": {
      "model": "deepseek-ai/DeepSeek-V4.1-Flash-1017",
      "model_revision": "1bae0e1088993b9b82de08f59de5be5a34e42170",
      "hardware": null,
      "executed_runtime_revision": null,
      "input_tokens": null,
      "output_tokens": null,
      "repetitions": null,
      "measurement_scope": "publisher capability evaluation, not local speed",
      "benchmark": "HLE without tools",
      "population": "full set",
      "tools": false
    },
    "evidence_state": "source_reported",
    "site_reproduced": false,
    "evidence_url": "https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash-1017/blob/1bae0e1088993b9b82de08f59de5be5a34e42170/README.md#L51",
    "source_document_sha256": "b72b796e4f4c739eca5d0ad360a7679b39118ca7eb64891f7151a527b292c42a"
  },
  {
    "label": "HLE without tools, text-only subset",
    "metric": "HLE",
    "value": 44.0,
    "unit": "reported score",
    "statistic": "reported value",
    "uncertainty": null,
    "conditions": {
      "model": "deepseek-ai/DeepSeek-V4.1-Flash-1017",
      "model_revision": "1bae0e1088993b9b82de08f59de5be5a34e42170",
      "hardware": null,
      "executed_runtime_revision": null,
      "input_tokens": null,
      "output_tokens": null,
      "repetitions": null,
      "measurement_scope": "publisher capability evaluation, not local speed",
      "benchmark": "HLE without tools",
      "population": "text-only subset",
      "tools": false
    },
    "evidence_state": "source_reported",
    "site_reproduced": false,
    "evidence_url": "https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash-1017/blob/1bae0e1088993b9b82de08f59de5be5a34e42170/README.md#L51",
    "source_document_sha256": "b72b796e4f4c739eca5d0ad360a7679b39118ca7eb64891f7151a527b292c42a"
  },
  {
    "label": "DeepSWE v1.1",
    "metric": "DeepSWE",
    "value": 77.0,
    "unit": "reported score",
    "statistic": "reported value",
    "uncertainty": null,
    "conditions": {
      "model": "deepseek-ai/DeepSeek-V4.1-Flash-1017",
      "model_revision": "1bae0e1088993b9b82de08f59de5be5a34e42170",
      "hardware": null,
      "executed_runtime_revision": null,
      "input_tokens": null,
      "output_tokens": null,
      "repetitions": null,
      "measurement_scope": "publisher capability evaluation, not local speed",
      "benchmark": "DeepSWE v1.1",
      "harness": "Mini-SWE-V2"
    },
    "evidence_state": "source_reported",
    "site_reproduced": false,
    "evidence_url": "https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash-1017/blob/1bae0e1088993b9b82de08f59de5be5a34e42170/README.md#L53",
    "source_document_sha256": "b72b796e4f4c739eca5d0ad360a7679b39118ca7eb64891f7151a527b292c42a"
  },
  {
    "label": "Terminal-Bench 4.0",
    "metric": "Terminal_Bench",
    "value": 42.3,
    "unit": "reported score",
    "statistic": "reported value",
    "uncertainty": null,
    "conditions": {
      "model": "deepseek-ai/DeepSeek-V4.1-Flash-1017",
      "model_revision": "1bae0e1088993b9b82de08f59de5be5a34e42170",
      "hardware": null,
      "executed_runtime_revision": null,
      "input_tokens": null,
      "output_tokens": null,
      "repetitions": null,
      "measurement_scope": "publisher capability evaluation, not local speed",
      "benchmark": "Terminal-Bench 4.0",
      "harness": "Claude Code"
    },
    "evidence_state": "source_reported",
    "site_reproduced": false,
    "evidence_url": "https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash-1017/blob/1bae0e1088993b9b82de08f59de5be5a34e42170/README.md#L52",
    "source_document_sha256": "b72b796e4f4c739eca5d0ad360a7679b39118ca7eb64891f7151a527b292c42a"
  }
]
```