- Size
- 685B 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
- 24 Mar 2025the date the repo was created
- Context length
- 160k tokensfrom the model's config
- Kind
- Base model (no base model declared on the Hub)DeepseekV3ForCausalLM
- On Hugging Face
- deepseek-ai/DeepSeek-V3-0324145k downloads in the last 30 days, 3.2k likes
Scores
- default setting67.6%±2.71 Apr 2025, log
Epoch's name: DeepSeek-V3-0324. Best closed model on this set: gpt-6.2-astra_max, 96.8% (OpenAI). All 341 results
- default setting75.5%±0.91 Apr 2025, log
Epoch's name: DeepSeek-V3-0324. Best closed model on this set: gpt-5-2025-08-07_high, 98.1% (OpenAI). All 108 results
- default setting37.8%±6.21 Apr 2025, log
Epoch's name: DeepSeek-V3-0324. Best closed model on this set: claude-fable-5_high, 100.0% (Anthropic). All 318 results
- Edit format: diff55.1%24 Mar 2025, aider.chat
Epoch's name: DeepSeek-V3-0324. Best closed model on this set: gpt-5-2025-08-07_high, 88.0% (OpenAI). All 72 results
- default setting0.0%via Epoch AI
Epoch's name: DeepSeek-V3-0324. Best closed model on this set: gemini-4-carbon_high, 36.0% (Google DeepMind). All 271 results
- default setting64.8%conceptualreasoning.ai
Epoch's name: DeepSeek-V3-0324. Best closed model on this set: claude-fable-5-2_unknown, 99.2% (Anthropic). All 241 results
- default setting50.0%Fiction.live leaderboard
Epoch's name: chutes/DeepSeek-V3-0324. Best closed model on this set: gpt-5-2025-08-07_medium, 97.2% (OpenAI). All 61 results
- default setting77.0%lechmazur/writing Github repository
Epoch's name: DeepSeek-V3-0324. Best closed model on this set: gpt-5-2025-08-07_medium, 86.0% (OpenAI). All 49 results
- default setting66.9%LiveBench Leaderboard
Epoch's name: DeepSeek-V3-0324. Best closed model on this set: gemini-2.5-pro-exp-03-25, 82.3% (Google DeepMind). All 54 results
- default setting15.5%10.5 to 20.5conceptualreasoning.ai
Epoch's name: DeepSeek-V3-0324. Best closed model on this set: claude-fable-5-2_xhigh, 70.6% (Anthropic). All 203 results
- default setting49.6%METR - Measuring AI Ability to Complete Long Tasks
Epoch's name: DeepSeek-V3-0324. Best closed model on this set: claude-mythos-preview-early, 85.2% (Anthropic). All 49 results
- default setting27.2%SimpleBench Leaderboard
Epoch's name: DeepSeek-V3-0324. Best closed model on this set: claude-fable-5-2_unknown, 94.9% (Anthropic). All 125 results
- default setting36.1%±0.0htihle.github.io
Epoch's name: DeepSeek-V3-0324. 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: 0.54 GB, worked out from the model's config (deepseek-ai/DeepSeek-V3-0324), 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
MaziyarPanahi/DeepSeek-V3-0324-GGUF (converted by MaziyarPanahi), 38k downloads. Sizes are the real files on the Hub, all parts added up.
| Format | Size | Memory needed | Get it |
|---|---|---|---|
| IQ1_S | 124.4 GBfile size, 9 parts | 125.4 GB124.4 + 0.54 + 0.50 | Commandsllama.cpp llama-server -hf MaziyarPanahi/DeepSeek-V3-0324-GGUF:IQ1_SDownload hf download MaziyarPanahi/DeepSeek-V3-0324-GGUF --include "DeepSeek-V3-0324.IQ1_S.gguf-*-of-00009.gguf" --local-dir DeepSeek-V3-0324-GGUF |
| IQ1_M | 138.7 GBfile size, 9 parts | 139.7 GB138.7 + 0.54 + 0.50 | Commandsllama.cpp llama-server -hf MaziyarPanahi/DeepSeek-V3-0324-GGUF:IQ1_MDownload hf download MaziyarPanahi/DeepSeek-V3-0324-GGUF --include "DeepSeek-V3-0324.IQ1_M.gguf-*-of-00009.gguf" --local-dir DeepSeek-V3-0324-GGUF |
| Q2_K | 227.3 GBfile size, 9 parts | 228.3 GB227.3 + 0.54 + 0.50 | Commandsllama.cpp llama-server -hf MaziyarPanahi/DeepSeek-V3-0324-GGUF:Q2_KDownload hf download MaziyarPanahi/DeepSeek-V3-0324-GGUF --include "DeepSeek-V3-0324.Q2_K.gguf-*-of-00009.gguf" --local-dir DeepSeek-V3-0324-GGUF |
| Q3_K_S | 269.2 GBfile size, 9 parts | 270.3 GB269.2 + 0.54 + 0.50 | Commandsllama.cpp llama-server -hf MaziyarPanahi/DeepSeek-V3-0324-GGUF:Q3_K_SDownload hf download MaziyarPanahi/DeepSeek-V3-0324-GGUF --include "DeepSeek-V3-0324.Q3_K_S.gguf-*-of-00009.gguf" --local-dir DeepSeek-V3-0324-GGUF |
MLX for Apple silicon
| Format | Size | Memory needed | Repo |
|---|---|---|---|
| MLX 5bitmlx-community/DeepSeek-V3-0324-5bit | 429.8 GBfile size | 430.8 GB429.8 + 0.54 + 0.50 | Download page |
Original weights size from the safetensors header, for vLLM, SGLang, Transformers
| Format | Size | Memory needed | Repo |
|---|---|---|---|
| F8_E4M3original weights | 641.3 GBfile size | 642.3 GB641.3 + 0.54 + 0.50 |
hf download deepseek-ai/DeepSeek-V3-0324 --local-dir DeepSeek-V3-0324Other conversions (5; sizes not read)
- unsloth/DeepSeek-V3-0324 FP8, 208 downloads
- QuixiAI/DeepSeek-V3-0324-AWQ AWQ, 179 downloads
- nebius/MTP-DeepSeek-V3-0324 FP8, 173 downloads
- jasonyux/DeepSeek-V3-0324-AWQ AWQ, 128 downloads
- CPU-Hybrid-MoE/DeepSeek-V3-0324-GPU-FP8-GPTQ4 GPTQ, fp8, 104 downloads
The Hub tags 26 quantised repos as conversions of this model; we read the most downloaded and show the maker's own first.
Run it by API
3 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 | $0.24 | $0.90 | 160k | not given | 94 | 0.7 s | ? | yes | yes |
| SiliconFlow | $0.25 | $1.00 | 160k | fp8 | 20 | 2.0 s | 99.8% | 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-V3-0324: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.
- nvidia/DeepSeek-V3-0324-NVFP49.2kUnreviewed
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.