Up to date
deepseek-ai DeepSeek License (deepseek-license) 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 #495 in LLMs · score 76.7 method v1 Sources 3 Downloads 30d 4.7k · #547 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: 12 quantized builds and 79 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 (2024-06-14), amber triangles are 8 dated articles (each links to it), grey ticks are repo commits.
13 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.
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:2401.06066 |
| License | DeepSeek License (deepseek-license) (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-Coder-V2-Instruct: 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.
Base model: deepseek-ai/DeepSeek-Coder-V2-Base
quantized: 12finetune: 1
| Variant | Relation | Quant | Params | Band | License | Author | Likes | Downloads |
|---|---|---|---|---|---|---|---|---|
| bartowski/DeepSeek-Coder-V2-Instruct-GGUF | quantized | GGUF | — | — | other | bartowski | 36 | 100.5k |
| qwp4w3hyb/DeepSeek-Coder-V2-Instruct-iMat-GGUF | quantized | GGUF | — | — | other | qwp4w3hyb | 2 | 78.8k |
| legraphista/DeepSeek-Coder-V2-Instruct-IMat-GGUF | quantized | GGUF | — | — | other | legraphista | 6 | 33.6k |
| second-state/DeepSeek-Coder-V2-Instruct-GGUF | quantized | GGUF | — | — | other | second-state | 1 | 27.7k |
| gaianet/DeepSeek-Coder-V2-Instruct-GGUF | quantized | GGUF | — | — | other | gaianet | 0 | 9.1k |
| nisten/deepseek-coder-v2-inst-cpu-optimized-gguf | quantized | gguf | — | — | — | nisten | 5 | 7.6k |
| mradermacher/DeepSeek-Coder-V2-Instruct-i1-GGUF | quantized | GGUF | — | — | other | mradermacher | 7 | 5.3k |
| GGorman/DeepSeek-Coder-V2-Instruct-Q4-mlx | quantized | mlx | 236B | XXL | other | GGorman | 1 | 2.5k |
| nafisabdkhan/DeepSeek-Coder-V2-Instruct-mlx-3Bit | quantized | mlx | 236B | XXL | other | nafisabdkhan | 0 | 2.5k |
| nafisabdkhan/DeepSeek-Coder-V2-Instruct-mlx-4Bit | quantized | mlx | 236B | XXL | other | nafisabdkhan | 0 | 1.8k |
| nafisabdkhan/DeepSeek-Coder-V2-Instruct-mlx-2Bit | quantized | mlx | 236B | XXL | other | nafisabdkhan | 0 | 1.5k |
| Ocean82/deepseek-coder-v2-inst-cpu-optimized-gguf | quantized | gguf | — | — | — | Ocean82 | 1 | 1.4k |
| mradermacher/DeepSeek-Coder-V2-Instruct-GGUF | finetune | GGUF | — | — | other | mradermacher | 8 | 0 |
| Date | Commit | SHA |
|---|---|---|
| 2024-08-21 | Add base_model metadata (#8) | 2453c79 |
| 2024-07-03 | Update README.md | 4aede65 |
| 2024-06-24 | Update modeling_deepseek.py | 601f33f |
| 2024-06-19 | Update README.md | 5de46fd |
| 2024-06-18 | Update README.md | 7a1063a |
| 2024-06-18 | Update README.md | a219823 |
| 2024-06-17 | Update README.md | ba087e2 |
| 2024-06-17 | Update README.md | ee736e8 |
| 2024-06-16 | Create README.md | bc8583c |
| 2024-06-14 | Upload folder using huggingface_hub | 3cdad23 |
| 2024-06-14 | initial commit | eb68607 |
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 21:40 UTC · Providers: 2026-10-24 21:44 UTC · Articles: 2026-10-24 21:46 UTC · Summary: 2026-10-07 15:11 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.
