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 #614 in LLMs · score 73.8 method v1 Sources 3 Downloads 30d 4.5k · #552 of 619 tracked
Picked by rule from 1 tracked piece: the lab's own post, the most shared, a field report, the latest.
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: 8 quantized builds and 68 Spaces.
Top Spaces running it: KBaba7/Quant ♥ 51 · FallnAI/Quantize-HF-Models ♥ 19 · bhaskartripathi/LLM_Quantization ♥ 16 · openfree/LLM_Quantization ♥ 16
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 (2024-09-05), amber triangles are 1 dated article (each links to it), grey ticks are repo commits.
17 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 Aider Polyglot · Write code with agents | 72.2 | — | model author | 2026-10-07 |
| author-reported AlignBench | 8.04 | — | model author | 2026-10-07 |
| author-reported AlpacaEval · Chat and follow instructions | 50.5 | — | model author | 2026-10-07 |
| author-reported Arena-Hard · Chat and follow instructions | 76.2 | — | model author | 2026-10-07 |
| author-reported DS-Arena-Code | 63.1 | — | model author | 2026-10-07 |
| author-reported DS-FIM-Eval | 78.3 | — | model author | 2026-10-07 |
| author-reported HumanEval · Write code with agents | 89 | — | model author | 2026-10-07 |
| author-reported HumanEval · Write code with agents | 73.8 | — | model author | 2026-10-07 |
| author-reported LiveCodeBench · Write code with agents | 41.8 | — | model author | 2026-10-07 |
| author-reported MT-Bench · Chat and follow instructions | 9.02 | — | model author | 2026-10-07 |
| author-reported SWE-bench Verified · Write code with agents | 16.8 | — | 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 |
| 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-V2.5: 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: 8finetune: 7adapter: 2
| Variant | Relation | Quant | Params | Band | License | Author | Likes | Downloads |
|---|---|---|---|---|---|---|---|---|
| mlx-community/DeepSeek-V2.5-MLX-AQ4_1_64 | quantized | MLX | 236B | XXL | other | mlx-community | 2 | 958.3k |
| bartowski/DeepSeek-V2.5-GGUF | quantized | GGUF | — | — | other | bartowski | 43 | 337.8k |
| MaziyarPanahi/DeepSeek-V2.5-GGUF | quantized | GGUF | — | — | — | MaziyarPanahi | 3 | 254.2k |
| legraphista/DeepSeek-V2.5-IMat-GGUF | quantized | GGUF | — | — | other | legraphista | 4 | 34.4k |
| second-state/DeepSeek-V2.5-GGUF | quantized | GGUF | — | — | other | second-state | 0 | 11.3k |
| lmstudio-community/DeepSeek-V2.5-GGUF | quantized | GGUF | — | — | other | lmstudio-community | 11 | 9.4k |
| bullerwins/DeepSeek-V2.5-GGUF | quantized | GGUF | — | — | other | bullerwins | 2 | 2.4k |
| mradermacher/DeepSeek-V2.5-i1-GGUF | quantized | GGUF | — | — | other | mradermacher | 2 | 991 |
| ericfjl/chatQiBo | finetune | — | — | — | apache-2.0 | ericfjl | 0 | 0 |
| mradermacher/DeepSeek-V2.5-GGUF | finetune | GGUF | — | — | other | mradermacher | 0 | 0 |
| CK85/Ck85 | finetune | — | — | — | openrail | CK85 | 0 | 0 |
| LfaNick7907/Liliana | finetune | — | — | — | apache-2.0 | LfaNick7907 | 0 | 0 |
| louferbrasbs4pro/Alice | finetune | — | — | — | apache-2.0 | louferbrasbs4pro | 0 | 0 |
| Bahridd/Gurdofarid | adapter | — | — | — | mit | Bahridd | 0 | 0 |
| DomedyYesDom/A-test | adapter | — | — | — | mit | DomedyYesDom | 0 | 0 |
| aleksaDam997/insuranceAPI | finetune | — | — | — | — | aleksaDam997 | 0 | 0 |
| boltzmzn/han | finetune | — | — | — | bsl-1.0 | boltzmzn | 0 | 0 |
| Date | Commit | SHA |
|---|---|---|
| 2024-12-11 | Update tokenizer_config.json | c85b5ed |
| 2024-10-08 | Update metadata (#9) | 98b1184 |
| 2024-09-06 | Update README.md | 24b08cb |
| 2024-09-06 | Update README.md | 594d86b |
| 2024-09-06 | Update README.md | 5941330 |
| 2024-09-06 | Update tokenizer.json | cb6425f |
| 2024-09-05 | Upload folder using huggingface_hub | a05fd5f |
| 2024-09-05 | initial commit | 83646f4 |
Ranked by source signals (HN, Lobsters, authority domains, official posts) and recency.
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.
