- 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
- 29 Sep 2025the date the repo was created
- Context length
- 160k tokensfrom the model's config
- Fine-tune
- of deepseek-ai/DeepSeek-V3.2-Exp-BaseDeepseekV32ForCausalLM
- On Hugging Face
- deepseek-ai/DeepSeek-V3.2-Exp56k downloads in the last 30 days, 1.0k likes
Scores
- effort thinking; Edit format: diff74.2%Aider LLM Leaderboards
- Edit format: diff70.2%Aider LLM Leaderboards
Epoch's name: DeepSeek-V3.2-Exp. Best closed model on this set: gpt-5-2025-08-07_high, 88.0% (OpenAI). All 72 results
- effort thinking13.2%via Epoch AI
Epoch's name: DeepSeek-V3.2-Exp. Best closed model on this set: gpt-5.4-2026-03-05_xhigh, 27.9% (OpenAI). All 23 results
- effort thinking9.5%via Epoch AI
Epoch's name: DeepSeek-V3.2-Exp. Best closed model on this set: gpt-5.5_high, 22.2% (OpenAI). All 17 results
- effort thinking2.9%via Epoch AI
Epoch's name: DeepSeek-V3.2-Exp. Best closed model on this set: gemini-4-carbon_high, 36.0% (Google DeepMind). All 271 results
- effort thinking87.7%conceptualreasoning.ai
Epoch's name: DeepSeek-V3.2-Exp. Best closed model on this set: claude-fable-5-2_unknown, 99.2% (Anthropic). All 241 results
- effort high83.3%Fiction.live leaderboard
- default setting52.8%Fiction.live leaderboard
Epoch's name: DeepSeek-V3.2-Exp. Best closed model on this set: gpt-5-2025-08-07_medium, 97.2% (OpenAI). All 61 results
- effort thinking29.1%24.4 to 33.8conceptualreasoning.ai
Epoch's name: DeepSeek-V3.2-Exp. Best closed model on this set: claude-fable-5-2_xhigh, 70.6% (Anthropic). All 203 results
- Environment model: Qwen_Plus42.9%13 Oct 2025, TheAgentCompany leaderboard
Epoch's name: DeepSeek-V3.2-Exp. Best closed model on this set: gemini-2.5-flash-preview-09-2025, 41.1% (Google DeepMind). All 16 results
- effort thinking39.5%±0.0htihle.github.io
Epoch's name: DeepSeek-V3.2-Exp. 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-V3.2-Exp), at 16-bit precision. Choose a machine above to see a verdict for each format. Method
Estimated sizes no measured GGUF files for this model
From the parameter count and the bits per weight of each level (the median measured over the GGUF files in our snapshot, or the format's block size). Real files differ by a few per cent.
| Format | Size | Memory needed | Repo |
|---|---|---|---|
| Q4_K_M4.88 bits per weight, measured median | 389.3 GBestimated | 390.3 GB389.3 + 0.54 + 0.50 | |
| Q5_K_M5.71 bits per weight, measured median | 455.6 GBestimated | 456.6 GB455.6 + 0.54 + 0.50 | |
| Q6_K6.57 bits per weight, measured median | 524.1 GBestimated | 525.2 GB524.1 + 0.54 + 0.50 | |
| Q8_08.50 bits per weight, measured median | 678.5 GBestimated | 679.6 GB678.5 + 0.54 + 0.50 |
Original weights size from the safetensors header, for vLLM, SGLang, Transformers
| Format | Size | Memory needed | Repo |
|---|---|---|---|
| F8_E4M3original weights | 642.1 GBfile size | 643.2 GB642.1 + 0.54 + 0.50 |
hf download deepseek-ai/DeepSeek-V3.2-Exp --local-dir DeepSeek-V3.2-ExpOther conversions (3; sizes not read)
- QuantTrio/DeepSeek-V3.2-Exp-AWQ AWQ, 175 downloads
- libraos/DeepSeek-V3.2-Exp-AWQ AWQ, 42 downloads
- QuantTrio/DeepSeek-V3.2-Exp-AWQ-Lite AWQ, 39 downloads
The Hub tags 3 quantised repos as conversions of this model; we read the most downloaded and show the maker's own first.
Run it by API
1 provider serves 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 |
|---|---|---|---|---|---|---|---|---|---|
| SiliconFlow | $0.27 | $0.41 | 160k | fp8 | 16 | 2.2 s | 99.2% | yes | yes |
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-V3.2-Exp:siliconflow", "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.