Model reference · open weights
DeepSeek-Flash-1017 is an open-weight language model from DeepSeek. DeepSeek-V4.1-Flash-1017 (FP8) weighs 510 GB; the smallest configuration that runs it is 8× H100 80 GB.
For self-hosting, compare this build's requirements below with the GPU you plan to rent.
DeepSeek-Flash-1017 is an image-text-to-text model developed by DeepSeek with 763.2 billion parameters. It supports a context length of 1,048,576 tokens and is distributed under the MIT license.
Summary of the deepseek-ai/DeepSeek-V4.1-Flash-1017 model card, 2026-10-18
What it is
| Released by | DeepSeek |
|---|---|
| Released | 2026-10-17 |
| Parameters | 763.2B |
| VRAM | 510 GB for the weights |
What it runs on
| Card | Requests at once | Context max | Memory | |
|---|---|---|---|---|
| 8K each | 32K each | |||
| RTX 3060 12 GB … B200 180 GB 12 smaller cards | ||||
| 8× H100 80 GB tensor parallel | 6 | 1 | 53K | 78.1 GB a card |
| 8× A100 80 GB tensor parallel · FP8 without its speed-up here | 17 | 4 | 136K | 78.2 GB a card |
| 4× B200 180 GB tensor parallel | 51 | 12 | 410K | 176 GB a card |
| 8× H200 141 GB tensor parallel | 95 | 23 | 767K | 138 GB a card |
| Requests at once | 8K tokens each | 32K tokens each |
|---|---|---|
| 1 | 514 GB | 516 GB |
| 5 | 517 GB | 527 GB |
| 8 | 519 GB | 535 GB |
| 16 | 524 GB | 556 GB |
| 32 | 535 GB | 599 GB |
| 64 | 556 GB | 685 GB |
One card, with vLLM's small-card settings.
From the model card
DeepSeek-V4.1-Flash-1017 is a minor update to DeepSeek-V4.1-Flash, delivering substantial improvements across reasoning, coding, agentic tasks, and visual benchmarks. Alongside these gains, the model reduces task execution time and output length, enabling users to complete tasks faster and at lower cost and advancing the performance–cost Pareto frontier across multiple agent harnesses.
| Benchmark | DS-V4.1-Flash-1017 | DS-V4.1-Flash | K3 | GLM-5.3 | GPT-5.6 Sol | Opus 5 |
|---|---|---|---|---|---|---|
| HLE w/o tools | 42.6 (44.0†) | 36.8 (39.1†) | 43.5 | 42.0† | 44.5 | 56.3 |
| Terminal-Bench 4.0 | 42.3 | 31.2 | 12.6 | 37.9 | 39.9 | 51.8 |
| DeepSWE v1.1 | 77.0 | 74.2 | 67.5 | 66.9 | 73.0 | 74.0 |
| ProgramBench | 29.1 | 20.3 | 17.5 | 19.0 | 23.0 | 37.0 |
| NL2Repo-Bench | 68.2 | 65.4 | 58.0 | 58.0 | 56.8 | 75.3 |
| Automation-Bench v1.0.6 | 60.5 | 54.8 | 46.7 | 48.8 | 45.8 | 50.3 |
| Agents’ Last Exam | 35.4 | 31.8 | 27.6 | 28.5 | 26.7 | 28.6 |
| Apex Bench v1.1 | 72.1 | 64.6 | 47.8 | 56.6 | 54.3 | 65.8 |
| Chartography (w/tools) | 83.0 | 78.9 | 68.1 | — | 79.9 | 84.0 |
| BabyVision (w/tools) | 92.5 | 89.6 | 85.7 | — | 88.9 | 94.1 |
| ZeroBench-main (w/tools) | 51.0 | 49.0 | 41.0 | — | 53.0 | 52.0 |
† denotes the text-only subset of HLE. We use the Claude Code harness for Terminal-Bench 4.0 and the Mini-SWE-V2 harness for DeepSWE v1.1.
This release does not include a Jinja-format chat template. The encoding folder contains a self-contained Python reference implementation (encoding.py) with test cases for multi-turn conversations, tool calling, thinking mode, numeric reasoning effort, mid-conversation system messages, and interleaved image content.
For production use, we additionally release deepseek-recipe, a set of Rust libraries with Python bindings that provides the same prompt format as a maintained, protocol-aware toolkit. It converts Messages, Chat Completions, and Responses API requests into the Conversation format, encodes them into DeepSeek V4 and V4.1 prompts or token IDs, and parses model output back into complete or streamed responses — covering thinking, tool calls, images, and generation settings. Model inference, tool execution, and HTTP transport are left to the caller.
Please refer to the inference folder for instructions on weight conversion and running inference locally.
Recommended sampling parameters:
| Parameter | Value |
|---|---|
temperature | 1.0 |
top_p | 1.0 |
context_window | 1M tokens |
max_tokens | ≥ 256K |
This repository and the model weights are licensed under the MIT License.
@misc{deepseekai2026deepseekv41flash,
title={DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression},
author={DeepSeek-AI},
year={2026},
}
If you have any questions, please raise an issue or contact us at service@deepseek.com.
Quoted from the model card on Hugging Face. The full card is behind the Hugging Face link above.