- Size
- 763B parameterscounted from the safetensors header on the Hub
- Licence
- unknown, MIT LicenseOur reading, check the licence: You can use, change and redistribute the model for any purpose, including commercially. Keep the copyright notice and the licence text with copies. You do not have to share your changes.
- On the Hub since
- 10 Sep 2026the date the repo was created
- Context length
- 1M tokensfrom the model's config
- Kind
- Base model (no base model declared on the Hub)DeepseekV41ForCausalLM
- On Hugging Face
- deepseek-ai/DeepSeek-V4.1-Flash1.5M downloads in the last 30 days, 5.0k likes
Scores
- effort max48.0%±5.013 Oct 2026, log
Epoch's name: deepseek-v4.1-flash. Best closed model on this set: claude-fable-5-2_max, 79.0% (Anthropic). All 166 results
- effort max26.8%±7.08 Oct 2026, Epoch AI
Epoch's name: deepseek-v4.1-flash. Best closed model on this set: claude-fable-5-2_max, 100.0% (Anthropic). All 83 results
- effort max67.4%±2.88 Oct 2026, Epoch AI
Epoch's name: deepseek-v4.1-flash. Best closed model on this set: claude-fable-5-2_max, 95.1% (Anthropic). All 127 results
- effort max34.2%±6.08 Oct 2026, Epoch AI
Epoch's name: deepseek-v4.1-flash. Best closed model on this set: claude-fable-5-2_max, 90.0% (Anthropic). All 41 results
- effort max89.8%±1.79 Oct 2026, log
Epoch's name: deepseek-v4.1-flash. Best closed model on this set: gpt-6.2-astra_max, 96.8% (OpenAI). All 341 results
- effort max64.4%±11.421 Oct 2026, Epoch AI
Epoch's name: deepseek-v4.1-flash. Best closed model on this set: claude-sonnet-5-5_max, 97.8% (Anthropic). All 47 results
- effort max43.0%±5.08 Oct 2026, Epoch AI
Epoch's name: deepseek-v4.1-flash. Best closed model on this set: gpt-6.2-astra_max, 95.0% (OpenAI). All 148 results
- effort max98.3%±0.68 Oct 2026, log
Epoch's name: deepseek-v4.1-flash. Best closed model on this set: claude-fable-5_high, 100.0% (Anthropic). All 318 results
- effort max42.9%±1.613 Oct 2026, log
Epoch's name: deepseek-v4.1-flash. Best closed model on this set: claude-fable-5-2_max, 94.0% (Anthropic). All 105 results
- effort unknown39.5%via Epoch AI (error bar left out)
Epoch's name: deepseek-v4.1-flash. Best closed model on this set: gemini-4-carbon_unknown, 84.2% (Google DeepMind). All 66 results
- effort max94.5%arcprize.org
- effort low90.5%arcprize.org
- effort high88.5%arcprize.org
- effort none7.8%arcprize.org
Epoch's name: deepseek-v4.1-flash. Best closed model on this set: claude-fable-5_max, 98.5% (Anthropic). All 318 results
- effort max72.9%via Epoch AI
- effort high67.5%via Epoch AI
- effort low60.6%via Epoch AI
- effort none1.3%via Epoch AI
Epoch's name: deepseek-v4.1-flash. Best closed model on this set: gpt-6-astra_max, 95.0% (OpenAI). All 299 results
- effort max14.3%via Epoch AI
- effort none0.3%via Epoch AI
Epoch's name: deepseek-v4.1-flash. Best closed model on this set: gemini-4-carbon_high, 36.0% (Google DeepMind). All 271 results
- effort unknown89.9%conceptualreasoning.ai
Epoch's name: deepseek-v4.1-flash. Best closed model on this set: claude-fable-5-2_unknown, 99.2% (Anthropic). All 241 results
- effort high; Harness: devin-cli; Reasoning effort: high43.9%cognition.com
Epoch's name: deepseek-v4.1-flash. Best closed model on this set: claude-opus-5-5_medium, 54.6% (Anthropic). All 46 results
- effort unknown47.0%43.0 to 51.0conceptualreasoning.ai
Epoch's name: deepseek-v4.1-flash. Best closed model on this set: claude-fable-5-2_xhigh, 70.6% (Anthropic). All 203 results
- effort unknown54.0%vals.ai
Epoch's name: deepseek-v4.1-flash. Best closed model on this set: claude-fable-5-1_max, 100.0% (Anthropic). All 85 results
- effort unknown9.6%via Epoch AI
Epoch's name: deepseek-v4.1-flash. Best closed model on this set: claude-fable-5-2_unknown, 41.3% (Anthropic). All 20 results
- effort unknown66.7%simple-bench.com
Epoch's name: deepseek-v4.1-flash. Best closed model on this set: claude-fable-5-2_unknown, 94.9% (Anthropic). All 125 results
- effort high46.3%yhenon.github.io
Epoch's name: deepseek-v4.1-flash. Best closed model on this set: claude-fable-5_high, 95.0% (Anthropic). All 29 results
- effort high; Agent: opencode; Reasoning effort: high11.6%htihle.github.io
Epoch's name: deepseek-v4.1-flash. Best closed model on this set: claude-fable-5-2_xhigh, 65.3% (Anthropic). All 27 results
Claimed by the maker Claimed
The model card has no claimed scores in a machine-readable form (the card's model-index), so none are shown. The maker may give scores in the card text: read the card.
Other views, which we link to and do not copy: look this model up on Artificial Analysis and the Arena leaderboard.
Independent scores from Epoch AI (CC-BY 4.0), fetched 19 Nov 2026: Epoch AI, ‘Capabilities & benchmarking’. Published online at epoch.ai. Retrieved from ‘https://epoch.ai/benchmarks’ [online resource]. Each row links its own source. What the badges mean.
Run it yourself
Memory needed = weights + context cache + 0.50 GB for the runtime. Context cache at 8k tokens: 0.63 GB, worked out from the model's config (deepseek-ai/DeepSeek-V4.1-Flash), at 16-bit precision. Choose a machine above to see a verdict for each format. Method
GGUF for llama.cpp, Ollama, LM Studio and others
antirez/deepseek-v4.1-flash-gguf (converted by antirez), 767k downloads. Sizes are the real files on the Hub, all parts added up.
| Format | Size | Memory needed | Get it |
|---|---|---|---|
| Q2 | 340.6 GBfile size | 341.7 GB340.6 + 0.63 + 0.50 | Commandsllama.cpp llama-server -hf antirez/deepseek-v4.1-flash-gguf:Q2Ollama ollama run hf.co/antirez/deepseek-v4.1-flash-gguf:Q2Download hf download antirez/deepseek-v4.1-flash-gguf --include "DeepSeek-V4.1-Flash-Q2.gguf" --local-dir deepseek-v4.1-flash-gguf |
| MXFP4 | 467.2 GBfile size, 9 parts | 468.3 GB467.2 + 0.63 + 0.50 | Commandsllama.cpp llama-server -hf antirez/deepseek-v4.1-flash-gguf:MXFP4Download hf download antirez/deepseek-v4.1-flash-gguf --include "DeepSeek-V4.1-Flash-1017-MXFP4-experts-*-of-00009.gguf" --local-dir deepseek-v4.1-flash-gguf |
MLX for Apple silicon
| Format | Size | Memory needed | Repo |
|---|---|---|---|
| MLX 2bitTensorFold/DeepSeek-V4.1-Flash-MLX-2bit-MTP | 222.4 GBfile size | 223.5 GB222.4 + 0.63 + 0.50 | Download page |
| MLXinferencerlabs/DeepSeek-V4.1-Flash-MLX-Q4i | 434.9 GBfile size | 436.1 GB434.9 + 0.63 + 0.50 | Download page |
Other conversions (19; sizes not read)
- nvidia/DeepSeek-V4.1-Flash-NVFP4 NVFP4, 34k downloads
- intel-ai/DeepSeek-V4.1-Flash-MXFP4-Mixed-CT-AutoRound Other, mxfp4, 12k downloads
- pfeifferj/DeepSeek-V4.1-Flash-GSQ-RCO-GGUF GGUF, 8.6k downloads
- Mia-AiLab/DeepSeek-V4.1-Flash-EXL3-2.9bpw EXL3, 2.6k downloads
- coolbho3k/DeepSeek-V4.1-Flash-GRAFT-3bpw Other, 2.2k downloads
- amd/DeepSeek-V4.1-Flash-Quark-MXFP4 Other, mxfp4, 1.1k downloads
- 0xSero/DeepSeek-V4.1-Flash-Spark EXL3, 229 downloads
- jayleaton/DeepSeek-V4.1-Flash-EXL3-2.8bpw EXL3, 220 downloads
- Mia-AiLab/DeepSeek-V4.1-Flash-EXL3-3.0bpw EXL3, 217 downloads
- LibertAIDAI/DeepSeek-V4.1-Flash-REAP-256E FP8, 216 downloads
- LibertAIDAI/DeepSeek-V4.1-Flash-NVFP4 NVFP4, 183 downloads
- tiny-random/deepseek-v4.1-flash FP8, 180 downloads
- amd/DeepSeek-V4.1-Flash-Quark-PTPC-FP8 FP8, 163 downloads
- Blackfrost-AI/DeepSeek-V4.1-Flash-DERISKED-FP8 FP8, 155 downloads
- INCModel3/DeepSeek-V4.1-Flash-W4A16-Engram-AutoRound GPTQ, w4a16, 155 downloads
- msuiche/DeepSeek-V4.1-Flash-NVFP4 NVFP4, 145 downloads
- lvkaokao/DeepSeek-V4.1-Flash-W4A16-Engram-AutoRound GPTQ, w4a16, 136 downloads
- INCModel3/DeepSeek-V4.1-Flash-MXFP4-Engram-AutoRound Other, mxfp4, 104 downloads
- aidendle94/DeepSeek-V4.1-Flash-NVFP4-Engram NVFP4, 95 downloads
The Hub tags 100 or more quantised repos as conversions of this model; we read the most downloaded and show the maker's own first.
Run it by API
23 providers serve this model through the Hugging Face router. Prices are US dollars per million tokens. Precision is what the provider reports; a lower precision than the original weights can change answers. Live first, then cheapest output.
| Provider | In | Out | Context | Precision | Tokens/s | First token | Uptime 24h | Tools | JSON |
|---|---|---|---|---|---|---|---|---|---|
| DeepInfra | $0.14 | $0.42 | 1M | fp8 | 107 | 0.6 s | 100.0% | yes | yes |
| Novita | $0.12 | $0.48 | 1M | fp8 | 115 | 1.0 s | 100.0% | yes | yes |
| River | $0.12 | $0.48 | 1M | not given | 125 | 0.7 s | 99.9% | yes | yes |
| Relace | $0.12 | $0.50 | 1M | fp4 | 115 | 0.7 s | 100.0% | yes | yes |
| Wafer | $0.051 | $0.57 | 1M | mxfp4 | 166 | 0.3 s | 100.0% | yes | yes |
| InferenceNet | $0.10 | $0.60 | 1016k | fp8 | 145 | 0.3 s | 100.0% | yes | yes |
| Reka | $0.12 | $0.64 | 1M | not given | 80 | 0.3 s | 99.9% | yes | yes |
| CoreWeave | $0.13 | $0.65 | 1M | fp8 | 155 | 0.7 s | 100.0% | yes | yes |
| Cohere | $0.20 | $0.66 | 1M | fp8 | 181 | 0.6 s | 100.0% | yes | yes |
| Ionstream | $0.20 | $0.70 | 1M | not given | 202 | 0.7 s | 100.0% | yes | yes |
| Mancer 2 | $0.21 | $0.75 | 1M | fp8 | 92 | 0.7 s | 100.0% | yes | yes |
| Fireworks | $0.21 | $0.84 | 1M | not given | 125 | 0.6 s | 98.2% | yes | yes |
| Cloudflare | $0.10 | $0.90 | 1M | not given | 95 | 1.8 s | 99.1% | yes | yes |
| DigitalOcean | $0.23 | $0.90 | 1M | not given | 177 | 0.7 s | 100.0% | yes | yes |
| OpenInference | $0.06 | $0.90 | 1M | fp4 | 145 | 0.8 s | 100.0% | yes | yes |
| BaseTen | $0.30 | $1.20 | 1M | not given | 182 | 0.5 s | 100.0% | yes | yes |
| Modal | $0.30 | $1.20 | 1M | not given | 78 | 1.2 s | 100.0% | yes | yes |
| Nebius | $0.30 | $1.20 | 1M | fp8 | 105 | 0.7 s | 100.0% | yes | yes |
| Parasail | $0.30 | $1.20 | 1M | fp8 | 209 | 0.5 s | 100.0% | yes | yes |
| SiliconFlow | $0.30 | $1.20 | 1M | fp8 | 124 | 1.7 s | 100.0% | yes | no |
| Together | $0.30 | $1.20 | 1M | not given | 243 | 0.2 s | 100.0% | yes | yes |
| Venice | $0.30 | $1.20 | 977k | fp8 | 139 | 0.6 s | 100.0% | yes | yes |
| featherless-ai | ? | ? | ? | not given | ? | ? | ? | not given | not given |
Through the router, with a Hugging Face token (the router bills your Hugging Face account). Change the name after the colon to pick another provider.
curl https://router.huggingface.co/v1/chat/completions \
-H "Authorization: Bearer $HF_TOKEN" -H "Content-Type: application/json" \
-d '{"model": "deepseek-ai/DeepSeek-V4.1-Flash:deepinfra", "messages": [{"role": "user", "content": "Hello"}]}'Not built yet: one key for every open model, with BlockRun, and our own tested-quality score per provider. Until then, precision and measured speed are the best guide to a provider here.
Fine-tunes of this model
Repos that declare this model as their base, most downloaded first. Listing is not a recommendation; unreviewed ones have not been checked.
- s-zaizen/DeepSeek-V4.1-Flash-Abliterated763B917Unreviewed
Planned for this page Not built yet
- Try it in private chat
- A link to Solana AI's confidential chat for the models it serves. This model is not listed as served there.
- Fine-tune it
- Fine-tuning a few base models from this page and publishing the result here.
- Creators and earnings
- Pages for people who publish fine-tunes and adapters of this model, and what they earn.
- Fund and bounties
- Bounties for new open models, paid from a public fund. How the fund will work.
- Contribute compute
- How to give compute to open model work, with Akash.
Model data from the Hugging Face Hub 19 Nov 2026, 13:43 UTC. The repo. Found a mistake on this page? Tell us.