- Size
- 1.6T 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
- 22 Apr 2026the date the repo was created
- Context length
- 1M tokensfrom the model's config
- Kind
- Base model (no base model declared on the Hub)DeepseekV4ForCausalLM
- On Hugging Face
- deepseek-ai/DeepSeek-V4-Pro321k downloads in the last 30 days, 5.7k likes
Scores
- effort max19.0%±3.913 Oct 2026, log
- effort high16.0%±3.713 Oct 2026, log
- effort none4.0%±2.013 Oct 2026, log
Epoch's name: deepseek-v4-pro. Best closed model on this set: claude-fable-5-2_max, 79.0% (Anthropic). All 166 results
- effort max2.4%±2.417 Jun 2026, log
Epoch's name: deepseek-v4-pro. Best closed model on this set: claude-fable-5-2_max, 100.0% (Anthropic). All 83 results
- effort max45.3%±3.017 Jun 2026, log
Epoch's name: deepseek-v4-pro. Best closed model on this set: claude-fable-5-2_max, 95.1% (Anthropic). All 127 results
- effort high90.9%±2.06 Aug 2026, log
- effort max89.6%±1.716 Jun 2026, log
- effort none73.2%±3.26 Aug 2026, log
Epoch's name: deepseek-v4-pro. Best closed model on this set: gpt-6.2-astra_max, 96.8% (OpenAI). All 341 results
- effort none17.0%±3.827 Aug 2026, log
Epoch's name: deepseek-v4-pro. Best closed model on this set: gpt-6.2-astra_max, 95.0% (OpenAI). All 148 results
- effort max96.7%±2.017 Jun 2026, log
- effort high95.6%±3.16 Aug 2026, log
- effort none46.7%±7.56 Aug 2026, log
Epoch's name: deepseek-v4-pro. Best closed model on this set: claude-fable-5_high, 100.0% (Anthropic). All 318 results
- effort max47.0%±1.627 Aug 2026, log
Epoch's name: deepseek-v4-pro. Best closed model on this set: claude-fable-5-2_max, 94.0% (Anthropic). All 105 results
- effort max77.6%±1.918 Jun 2026, log
Epoch's name: deepseek-v4-pro. Best closed model on this set: claude-opus-4-7_max, 83.5% (Anthropic). All 35 results
- effort high13.5%via Epoch AI
Epoch's name: deepseek-v4-pro. Best closed model on this set: gpt-5.5_high, 22.2% (OpenAI). All 17 results
- effort max12.9%via Epoch AI
- effort high10.0%via Epoch AI
Epoch's name: deepseek-v4-pro. Best closed model on this set: gemini-4-carbon_high, 36.0% (Google DeepMind). All 271 results
- effort max90.7%conceptualreasoning.ai
Epoch's name: deepseek-v4-pro. Best closed model on this set: claude-fable-5-2_unknown, 99.2% (Anthropic). All 241 results
- effort none; Harness: mini-swe-agent; Reasoning effort: none17.6%cognition.com
Epoch's name: deepseek-v4-pro. Best closed model on this set: claude-opus-5-5_medium, 54.6% (Anthropic). All 46 results
- effort max41.2%36.9 to 45.5conceptualreasoning.ai
Epoch's name: deepseek-v4-pro. Best closed model on this set: claude-fable-5-2_xhigh, 70.6% (Anthropic). All 203 results
- effort max; Reasoning effort: max16.0%±3.7vals.ai
Epoch's name: deepseek-v4-pro. Best closed model on this set: claude-fable-5-1_max, 100.0% (Anthropic). All 85 results
- effort high40.0%yhenon.github.io
Epoch's name: deepseek-v4-pro. Best closed model on this set: claude-fable-5_high, 95.0% (Anthropic). All 29 results
- effort max48.6%±0.0htihle.github.io
- effort high46.5%±0.0htihle.github.io
Epoch's name: deepseek-v4-pro. Best closed model on this set: gpt-6-astra_promax, 93.6% (OpenAI). All 173 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: 0.95 GB, worked out from the model's config (deepseek-ai/DeepSeek-V4-Pro), 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
teamblobfish/DeepSeek-V4-Pro-GGUF (converted by teamblobfish), 620 downloads. Sizes are the real files on the Hub, all parts added up.
| Format | Size | Memory needed | Get it |
|---|---|---|---|
| Q2_K | 534.7 GBfile size, 13 parts | 536.2 GB534.7 + 0.95 + 0.50 | Commandsllama.cpp llama-server -hf teamblobfish/DeepSeek-V4-Pro-GGUF:Q2_KDownload hf download teamblobfish/DeepSeek-V4-Pro-GGUF --include "Q2_K-XL/DeepSeek-V4-Pro-Q2_K-XL-*-of-00013.gguf" --local-dir DeepSeek-V4-Pro-GGUF |
| Q4_K_M | 889.0 GBfile size, 21 parts | 890.5 GB889.0 + 0.95 + 0.50 | Commandsllama.cpp llama-server -hf teamblobfish/DeepSeek-V4-Pro-GGUF:Q4_K_MDownload hf download teamblobfish/DeepSeek-V4-Pro-GGUF --include "Q4_K_M-XL/DeepSeek-V4-Pro-Q4_K_M-XL-*-of-00021.gguf" --local-dir DeepSeek-V4-Pro-GGUF |
| Q8_0 | 1557.0 GBfile size, 37 parts | 1558.5 GB1557.0 + 0.95 + 0.50 | Commandsllama.cpp llama-server -hf teamblobfish/DeepSeek-V4-Pro-GGUF:Q8_0Download hf download teamblobfish/DeepSeek-V4-Pro-GGUF --include "Q8_0/DeepSeek-V4-Pro-Q8_0-*-of-00037.gguf" --local-dir DeepSeek-V4-Pro-GGUF |
MLX for Apple silicon
| Format | Size | Memory needed | Repo |
|---|---|---|---|
| MLXinferencerlabs/DeepSeek-V4-Pro-MTP-MLX | 13.0 GBfile size | 14.5 GB13.0 + 0.95 + 0.50 | Download page |
| MLXmlx-community/DeepSeek-V4-Pro | 791.3 GBfile size | 792.8 GB791.3 + 0.95 + 0.50 | Download page |
Other conversions (13; sizes not read)
- nvidia/DeepSeek-V4-Pro-NVFP4 NVFP4, 38k downloads
- sgl-project/DeepSeek-V4-Pro-FP8 FP8, 8.0k downloads
- nvidia/DeepSeek-V4-Pro-nvfp4-DSpark NVFP4, 534 downloads
- intel-ai/DeepSeek-V4-Pro-MXFP4-Mixed-CT-AutoRound Other, mxfp4, 395 downloads
- unsloth/DeepSeek-V4-Pro FP8, 326 downloads
- RedHatAI/DeepSeek-V4-Pro-NVFP4-FP8 NVFP4, 303 downloads
- amd/DeepSeek-V4-Pro-NVFP4 NVFP4, 287 downloads
- m8than/DeepSeek-V4-Pro-E2M1-Furnace Other, 199 downloads
- amd/DeepSeek-V4-Pro-MXFP4 Other, mxfp4, 169 downloads
- wdfgyuagguf/DeepSeek-V4-Pro-NVFP4-FREE GGUF, nvfp4, 70 downloads
- Intel/DeepSeek-V4-Pro-W4A16-AutoRound Other, w4a16, 40 downloads
- nathanielthomas/DeepSeek-V4-Pro-FP8 FP8, 22 downloads
- ANetResearch/DeepSeek-V4-Pro-kllm FP8, 0 downloads
The Hub tags 31 quantised repos as conversions of this model; we read the most downloaded and show the maker's own first.
Run it by API
8 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 |
|---|---|---|---|---|---|---|---|---|---|
| Relace | $0.90 | $1.50 | 1M | fp4 | 94 | 0.9 s | 99.9% | yes | no |
| SiliconFlow | $0.90 | $1.70 | 1M | fp8 | 30 | 2.3 s | 99.9% | yes | no |
| DigitalOcean | $1.04 | $2.09 | 1M | not given | 40 | 1.1 s | 100.0% | yes | no |
| Novita | $1.28 | $2.56 | 1M | fp8 | 60 | 2.2 s | 100.0% | yes | no |
| DeepInfra | $1.30 | $2.60 | 1M | fp8 | 43 | 1.5 s | 99.9% | yes | yes |
| Venice | $1.65 | $3.30 | 977k | not given | 57 | 1.8 s | 95.2% | yes | yes |
| Azure | $1.91 | $3.83 | 1M | not given | 57 | 3.3 s | 100.0% | yes | no |
| 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-Pro:relace", "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.
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.