Up to date
deepseek-ai DeepSeek License (deepseek) out 3 years ago
16.4B parameters, text in, text out.
Verified 2026-10-25 Rank #683 in LLMs · score 72.4 method v1 Sources 3 Downloads 30d 24k · #443 of 619 tracked
Changed this week: 1 new quantized build on the Hub (17 in all).2026-10-24
Picked by rule from 9 tracked pieces: the lab's own post, the most shared, a field report, the latest.
The 2 picks above, plus these 7. 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: 17 quantized builds.
Weights only, an estimate: leave room for the KV cache. Method
About 9.8 GB at INT4, 20 GB at FP8, 39 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 (2024-01-09), amber triangles are 8 dated articles (each links to it).
18 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 | DeepseekForCausalLM |
| Model type | deepseek |
| Params by dtype | BF16: 16,375,728,128 |
| Size band | L |
| MoE | yes |
| Experts per token | 6 |
| Papers | arXiv:2401.06066 |
| License | DeepSeek License (deepseek) (other) |
| Hub snapshot | 2026-10-25 |
Weights-only memory for deepseek-moe-16b-chat: params × bytes/param × 1.2 overhead. KV cache and activations are extra. How this is computed.
| BF16 (2 bytes/param) | 39 GB · Single high-end GPU (<80 GB) |
|---|---|
| FP8 (1 byte/param) | 20 GB · Single GPU (<24 GB) |
| INT4 (0.5 bytes/param) | 9.8 GB · Single GPU (<24 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: 17finetune: 1
| Variant | Relation | Quant | Params | Band | License | Author | Likes | Downloads |
|---|---|---|---|---|---|---|---|---|
| mradermacher/deepseek-moe-16b-chat-i1-GGUF | quantized | GGUF | — | — | other | mradermacher | 0 | 19.6k |
| mradermacher/deepseek-moe-16b-chat-GGUF | quantized | GGUF | — | — | other | mradermacher | 3 | 7.4k |
| aclava/deepseek-moe-16b-chat-Q4_K_M-GGUF | quantized | GGUF | — | — | other | aclava | 1 | 5.7k |
| Lucy-in-the-Sky/deepseek-moe-16b-chat-Q4_K_M-GGUF | quantized | GGUF | — | — | other | Lucy-in-the-Sky | 1 | 2.1k |
| Lucy-in-the-Sky/deepseek-moe-16b-chat-Q8_0-GGUF | quantized | Q8_0 | — | — | other | Lucy-in-the-Sky | 0 | 1.9k |
| BlueMoonlight/deepseek-moe-16b-chat-mlx-4Bit | quantized | mlx | 16.4B | L | other | BlueMoonlight | 0 | 1.6k |
| noctrex/DeepSeek-MoE-16B-Chat-MXFP4_MOE-GGUF | quantized | GGUF | — | — | — | noctrex | 1 | 1.5k |
| amd/deepseek-moe-16b-chat-FP8-KV | quantized | -FP8 | 16.4B | L | other | amd | 0 | 864 |
| Lucy-in-the-Sky/deepseek-moe-16b-chat-Q6_K-GGUF | quantized | Q6_K | — | — | other | Lucy-in-the-Sky | 0 | 597 |
| soyrsoyr/deepseek-moe-16b-chat-W4A16-GPTQ | quantized | -W4A16 | 2.56B | M | other | soyrsoyr | 0 | 439 |
| Ibrahimarain/deepseek-moe-16b-chat-Q4_K_M-GGUF | quantized | GGUF | — | — | other | Ibrahimarain | 0 | 355 |
| Lucy-in-the-Sky/deepseek-moe-16b-chat-Q3_K_M-GGUF | quantized | GGUF | — | — | other | Lucy-in-the-Sky | 0 | 316 |
| soyrsoyr/deepseek-moe-16b-chat-W8A8-GPTQ | quantized | -W8A8 | 16.4B | L | other | soyrsoyr | 0 | 208 |
| soyrsoyr/deepseek-moe-16b-chat-NVFP4-GPTQ | quantized | NVFP4 | 9.41B | L | other | soyrsoyr | 0 | 155 |
| darkknight25/deepseek-16b-medical-GPT | finetune | — | — | — | mit | darkknight25 | 3 | 0 |
| Lucy-in-the-Sky/deepseek-moe-16b-chat-Q2_K-GGUF | quantized | Q2_K | — | — | other | Lucy-in-the-Sky | 0 | 142 |
| MIThridate/DeepSeek-MoE-16B-Chat-SAMI-AsymQ | quantized | GGUF | — | — | other | MIThridate | 0 | 92 |
| soyrsoyr/deepseek-moe-16b-chat-FP8-GPTQ | quantized | -FP8 | 16.4B | L | other | soyrsoyr | 0 | 73 |
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.
| Title | Source | Published | First seen | Signals |
|---|---|---|---|---|
| DeepSeek v4.1 Flash | twitter.com | 2026-09-10 | 2026-10-14 | hn |
| DeepSeek V4 Flash 0731 Intelligence, Performance and Price Analysis | artificialanalysis.ai | 2026-07-31 | 2026-10-14 | hn |
| DeepSeek OCR | github.com | 2025-10-20 | 2026-10-14 | hn |
| The path to open-sourcing the DeepSeek inference engine | github.com | 2025-04-14 | 2026-10-14 | hn |
| DeepSeek Open Infra: Open-Sourcing 5 AI Repos in 5 Days | github.com | 2025-02-21 | 2026-10-14 | hn |
| OpenAI says it has evidence DeepSeek used its model to train competitor | ft.com | 2025-01-29 | 2026-10-14 | hn |
| DeepSeek releases Janus Pro, a text-to-image generator [pdf] | github.com | 2025-01-27 | 2026-10-14 | hn |
| DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via RL | arxiv.org | 2025-01-25 | 2026-10-14 | hn |
| DeepSeek-R1 | github.com | 2025-01-20 | 2026-10-14 | hn |
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 · Providers: 2026-10-24 21:44 UTC · Articles: 2026-10-24 21:46 UTC · Summary: 2026-10-14 14:07 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.
