Get the latest setups
Models/DeepSeek V4/DeepSeek V4 Flash 0731
Text / deepseek-ai

DeepSeek V4 Flash 0731

DeepSeek V4 Flash 0731 is a text-generation model released under the MIT license on the deepseek-ai repository. It is described as the official release of DeepSeek-V4-Flash, superseding a preview version, with enhanced agentic capabilities. It shares the same model structure as DeepSeek-V4-Flash-DSpark and includes a speculative decoding module. The release does not include a Jinja-format chat template; instead, an encoding folder provides Python scripts and test cases for converting OpenAI-compatible messages to model inputs and parsing outputs. The reasoning_effort parameter supports three levels. Benchmark tables compare its reported scores with other models.

EstimatedRepository opened Jul 31, 2026Source checked 9/23/2026Version: 7872f01b
LOCALRENTED GPUOPEN WEIGHTS
Freshness 75 out of 100. Repository age: 76 days old, Jul 31, 2026. Measures age, not quality.
Popularity 90 out of 100. 4,416,319 downloads in 30 days; 4,083 lifetime likes. Checked Oct 15, 2026. Measures adoption, not quality.
What do these scores mean?

Two ways to compare models. Neither score measures answer quality, benchmark performance, or whether a model fits your machine.

Freshness · release age

A new release starts at 100. The score halves every 180 days: 100 × 2^(−age in days / 180). When the release date is unavailable, a repository date is a fallback—not proof of when the model was released. Missing dates stay unscored.

Check the date source
Popularity · adoption

Downloads over the past 30 days carry 80% of the score; lifetime likes carry 20%. Both use a logarithmic scale, capped at 10 million downloads and 100,000 likes. If likes are unavailable, downloads carry all the weight. Missing download statistics stay unscored.

round(80 × min(1, log10(1 + downloads) / 7) + 20 × min(1, log10(1 + likes) / 5))

Check the statistics source
Scores as of Oct 15, 2026. Statistics checked Oct 15, 2026. Statistics are marked for refresh after 72 hours.Full scoring method

At a glance

Parameters
304.18B
Architecture
deepseek_v4
Context length
1,048,576
License
mit
Disk space
155.4 GB
Software
SGLang, vLLM, Publisher PyTorch reference
View the model source
MY HARDWARE

Will it run on your machine?

Save your machine to see a personalized rating and its reasoning.

Add my hardware

Best for

  • Text generation
  • Agentic tasks
  • Code agent tasks
  • Tool-use benchmarks
  • Full-stack development tasks (internal DSBench)

Tradeoffs

  • Does not include a Jinja-format chat template
  • Requires the dedicated encoding folder for message encoding and output parsing
  • Speculative decoding module is included but no compatibility or performance details are provided
  • Numerical hardware requirements are not stated
  • Benchmark results are reported under specific evaluation settings and may not reflect other conditions

Ways to run it

SGLang · Linux

Repository-specific command in publisher documentation; confirm dependencies and hardware in the source.

sglang serve --trust-remote-code --model-path deepseek-ai/DeepSeek-V4-Flash-0731 --tp 4 --moe-runner-backend flashinfer_mxfp4 --speculative-algorithm DSPARK --mem-fraction-static 0.90 --chunked-prefill-size 4096 --swa-full-tokens-ratio 0.1
Official instructions

vLLM · Linux

Repository-specific command in publisher documentation; confirm dependencies and hardware in the source.

vllm serve deepseek-ai/DeepSeek-V4-Flash-0731 --trust-remote-code --kv-cache-dtype fp8 --block-size 256 --data-parallel-size 4 --enable-expert-parallel --moe-backend deep_gemm_mega_moe --attention-config '{"use_fp4_indexer_cache": true}' --speculative-config '{"method":"dspark","num_speculative_tokens":7,"draft_sample_method":"greedy"}'
Official instructions

Publisher PyTorch reference · Linux / rented GPU

Repository-specific command in publisher documentation; confirm dependencies and hardware in the source.

torchrun --nproc-per-node ${MP} generate.py --ckpt-path ${SAVE_PATH} --config ${CONFIG} --interactive
Official instructions

Explore its uses

SAFETENSORSTEXT-GENERATION

Keep exploring

Text
Prism ML

Bonsai 2 · 27B

A compressed 27B-class reasoning model with publisher-provided GGUF packs and a dedicated llama.cpp fork for CUDA, Metal, and CPU.

Freshness 90 out of 100. Release age: 28 days old, Sep 17, 2026. Measures age, not quality.
Popularity 90 out of 100. 4,849,199 downloads in 30 days; 2,697 lifetime likes. Checked Oct 15, 2026. Measures adoption, not quality.
MODEL SIZE27.36B
LOCALRENTED GPU
Released Sep 17, 2026
Text
DeepSeek

DeepSeek V4.1 Flash

A multimodal reasoning model with a compressed key-value cache, published as open weights.

Freshness 87 out of 100. Repository age: 35 days old, Sep 10, 2026. Measures age, not quality.
Popularity 84 out of 100. 1,238,583 downloads in 30 days; 4,519 lifetime likes. Checked Oct 15, 2026. Measures adoption, not quality.
Arena Open Source Text: rank 5 of 225. Ranked model: deepseek-v4.1-flash-max. Export dated Oct 13, 2026. Source checked Oct 15, 2026. Human preference ranking, not hardware suitability.+3
LOCALRENTED GPU
Repository opened Sep 10, 2026
Text
Qwen

Qwen3.8

Explore 4 versions of Qwen3.8. Compare model sizes, packages, hardware requirements, and available setups.

4 versionsCompare sizes & formats
LOCALRENTED GPU
Compare versions →