Up to date
deepseek-ai DeepSeek License (deepseek) out 2 years ago
236B parameters (6 of 160 experts per token), text in, text out, 160K tokens of context.
Verified 2026-10-25 Rank #552 in LLMs · score 74.9 method v1 Sources 3 Downloads 30d 28.7k · #429 of 619 tracked
Picked by rule from 8 tracked pieces: the lab's own post, the most shared, a field report, the latest.
The 2 picks above, plus these 6. Top is the radar's score: discussion, source authority and the lab's own posts, fading with age.
Hugging Face does not say who downloads a model or with what. These are the proxies: API providers listing it, quantized builds, fine-tunes/adapters/merges, and Spaces that load it.
No API provider serves it, so its downloads are people running it themselves: 2 quantized builds and 41 Spaces.
Top Spaces running it: allenai/WildBench ♥ 232 · allenai/ZebraLogic ♥ 95 · KBaba7/Quant ♥ 51 · FallnAI/Quantize-HF-Models ♥ 19
Weights only, an estimate: leave room for the KV cache. Method
About 141 GB at INT4, 283 GB at FP8, 566 GB at BF16: weights only, so leave room for the KV cache. Every expert must be resident, so total parameters count.
Estimate params × bytes per param × 1.2 · how we estimate
Weights, every dated article, and repo commits on one rail.
Teal is the weights (2024-04-28), amber triangles are 8 dated articles (each links to it), grey ticks are repo commits.
3 derivatives on the Hub. Which build to run, by runtime: the most downloaded in each class.
From the Hugging Face model tree; quantized builds in teal, fine-tunes, merges and adapters in greys.
Everything else, folded: the full tables, every source.
| Benchmark | Value | Setting / notes | Reported by | Date |
|---|---|---|---|---|
| author-reported BBH · Reason through hard problems | 78.9 | DeepSeek-V2 (MoE-236B) | model author | 2026-10-07 |
| author-reported BBH · Reason through hard problems | 81.3 | DeepSeek-V2 Chat (SFT) | model author | 2026-10-07 |
| author-reported C-Eval · Work across languages | 81.7 | DeepSeek-V2 (MoE-236B) | model author | 2026-10-07 |
| author-reported C-Eval · Work across languages | 80.9 | DeepSeek-V2 Chat (SFT) | model author | 2026-10-07 |
| author-reported CMMLU · Work across languages | 84 | DeepSeek-V2 (MoE-236B) | model author | 2026-10-07 |
| author-reported CMMLU · Work across languages | 82.4 | DeepSeek-V2 Chat (SFT) | model author | 2026-10-07 |
| author-reported GSM8K · Reason through hard problems | 79.2 | DeepSeek-V2 (MoE-236B) | model author | 2026-10-07 |
| author-reported GSM8K · Reason through hard problems | 90.8 | DeepSeek-V2 Chat (SFT) | model author | 2026-10-07 |
| author-reported HumanEval · Write code with agents | 48.8 | DeepSeek-V2 (MoE-236B) | model author | 2026-10-07 |
| author-reported HumanEval · Write code with agents | 76.8 | DeepSeek-V2 Chat (SFT) | model author | 2026-10-07 |
| author-reported LiveCodeBench · Write code with agents | 28.7 | DeepSeek-V2 Chat (SFT) | model author | 2026-10-07 |
| author-reported MATH-500 · Reason through hard problems | 43.6 | DeepSeek-V2 (MoE-236B) | model author | 2026-10-07 |
| author-reported MATH-500 · Reason through hard problems | 52.7 | DeepSeek-V2 Chat (SFT) | model author | 2026-10-07 |
| author-reported MBPP · Write code with agents | 66.6 | DeepSeek-V2 (MoE-236B) | model author | 2026-10-07 |
| author-reported MBPP · Write code with agents | 70.4 | DeepSeek-V2 Chat (SFT) | model author | 2026-10-07 |
| author-reported MMLU · Reason through hard problems | 78.5 | DeepSeek-V2 (MoE-236B) | model author | 2026-10-07 |
| author-reported MMLU · Reason through hard problems | 78.4 | DeepSeek-V2 Chat (SFT) | model author | 2026-10-07 |
| author-reported MMLU · Reason through hard problems | 77.8 | DeepSeek-V2 Chat (RL) | model author | 2026-10-07 |
Labels are evidence, not verdicts: measured a third-party leaderboard row for this model; author-reported a number the model author published in the card or eval files; structural a deterministic signal from the name, config or chat template, or a decision-model estimate. Each chip links to its source. All use cases.
| Pipeline tag | text-generation |
|---|---|
| Library | transformers |
| Architectures | DeepseekV2ForCausalLM |
| Model type | deepseek_v2 |
| Dtype | bfloat16 |
| Params by dtype | BF16: 235,741,434,880 |
| Size band | XXL |
| MoE | yes |
| Experts | 160 |
| Experts per token | 6 |
| Context length | 163,840 (config.json max_position_embeddings) |
| Papers | arXiv:2405.04434, arXiv:2311.18743 |
| License | DeepSeek License (deepseek) (other) |
| Hub snapshot | 2026-10-25 |
vLLM: supported · DeepseekV2ForCausalLM · 7050ef881ff0835f6890a47db1859a24c65481d6SGLang: supported · DeepseekV2ForCausalLM · 773cb938fe9484a8f7e7e46fb1b1fe96412c59ed
vLLM registry (7050ef881ff0835f6890a47db1859a24c65481d6) · SGLang registry (773cb938fe9484a8f7e7e46fb1b1fe96412c59ed) · Matched by architecture class name against each project's registry on main; 'supported' means the architecture is registered, not that this checkpoint was tested.
Weights-only memory for DeepSeek-V2-Chat: params × bytes/param × 1.2 overhead. KV cache and activations are extra. How this is computed.
| BF16 (2 bytes/param) | 566 GB · Multi-GPU node (<640 GB) |
|---|---|
| FP8 (1 byte/param) | 283 GB · Multi-GPU node (<640 GB) |
| INT4 (0.5 bytes/param) | 141 GB · Multi-GPU node (<640 GB) |
Weights only (params × bytes/param × 1.2 overhead); KV cache and activations extra. MoE: all experts must be resident, so total parameters count.
quantized: 2finetune: 1
| Variant | Relation | Quant | Params | Band | License | Author | Likes | Downloads |
|---|---|---|---|---|---|---|---|---|
| Wwayu/DeepSeek-V2-Chat-mlx-2Bit | quantized | mlx | 236B | XXL | other | Wwayu | 0 | 552 |
| mradermacher/DeepSeek-V2-Chat-i1-GGUF | quantized | GGUF | — | — | other | mradermacher | 1 | 352 |
| mradermacher/DeepSeek-V2-Chat-GGUF | finetune | GGUF | — | — | other | mradermacher | 1 | 0 |
| Date | Commit | SHA |
|---|---|---|
| 2024-06-08 | docs: update README.md | 8e3f5f6 |
| 2024-06-07 | docs: update README.md | 875361c |
| 2024-05-15 | Update README.md | 10bacc3 |
| 2024-05-09 | Merge branch 'main' of https://huggingface.co/deepseek-ai/DeepSeek-V2-Chat into main | 2b9af6b |
| 2024-05-09 | Update code & readme | 413b83f |
| 2024-05-08 | Update README.md | cfa9095 |
| 2024-05-08 | update citation info | 88a14de |
| 2024-05-07 | Update README.md | 896a24c |
| 2024-05-07 | Update README.md | bf3609a |
| 2024-05-07 | Update README.md | 161a2f2 |
| 2024-05-06 | Update model names | 2c190bb |
| 2024-05-06 | Update README.md | c10690d |
| 2024-05-06 | Update README.md | 0d2b17b |
| 2024-05-06 | Update README.md | 941577e |
| 2024-05-06 | Update README.md | 6e11005 |
| 2024-05-06 | Update README.md | 91c375a |
| 2024-05-06 | Update README.md | f1e9ce2 |
| 2024-05-06 | Create README.md | e67c544 |
| 2024-05-06 | Upload LICENSE | 00aa52d |
| 2024-05-06 | Upload folder using huggingface_hub | 6ba3505 |
| 2024-04-28 | initial commit | 0726502 |
Ranked by source signals (HN, Lobsters, authority domains, official posts) and recency. Summaries are generated from a stored copy of the article text; every sentence cites a span of that text, and nothing is shown that failed the citation check.
arXiv links found in the model card and its tags. "Peer-reviewed" is shown only with evidence: a published venue in OpenAlex (measured) or the authors' own journal reference on arXiv (reported).
Hub snapshot: 2026-10-25 · HF API: 2026-10-24 21:41 UTC · Providers: 2026-10-24 21:44 UTC · Articles: 2026-10-24 21:46 UTC · Summary: 2026-10-07 15:13 UTC · Last verified 2026-10-25
Email alerts are not open yet; the feeds above are the same data. See feeds for the item schema.
