Up to date
deepseek-ai DeepSeek License (deepseek) out 3 years ago
1.35B parameters, text in, text out, 16K tokens of context.
Verified 2026-10-25 Rank #560 in LLMs · score 74.8 method v1 Sources 3 Downloads 30d 35.8k · #408 of 619 tracked
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: 22 quantized builds and 100 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 0.8 GB at INT4, 1.6 GB at FP8, 3.2 GB at BF16: weights only, so leave room for the KV cache.
Estimate params × bytes per param × 1.2 · how we estimate
Weights, every dated article, and repo commits on one rail.
Teal is the weights (2023-10-29), amber triangles are 8 dated articles (each links to it), grey ticks are repo commits.
171 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.
The model is fine-tuned on 2B tokens of instruction data for conversational tasks.[1]
Generated 2026-10-07 15:13 UTC by parasail-gemma-4-26b-a4b-it; each numeral points at the fact it rests on. Not a verdict.
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.
Listed in LLMs
| Pipeline tag | text-generation |
|---|---|
| Library | transformers |
| Architectures | LlamaForCausalLM |
| Model type | llama |
| Dtype | bfloat16 |
| Params by dtype | BF16: 1,346,471,936 |
| Size band | S |
| MoE | no |
| Context length | 16,384 (config.json max_position_embeddings) |
| License | DeepSeek License (deepseek) (other) |
| Hub snapshot | 2026-10-25 |
vLLM: supported · LlamaForCausalLM · 7050ef881ff0835f6890a47db1859a24c65481d6SGLang: supported · LlamaForCausalLM · 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-1.3b-instruct: params × bytes/param × 1.2 overhead. KV cache and activations are extra. How this is computed.
| BF16 (2 bytes/param) | 3.2 GB · Edge (<4 GB) |
|---|---|
| FP8 (1 byte/param) | 1.6 GB · Edge (<4 GB) |
| INT4 (0.5 bytes/param) | 0.8 GB · Edge (<4 GB) |
Weights only (params × bytes/param × 1.2 overhead); KV cache and activations extra.
quantized: 22finetune: 87adapter: 61merge: 1
| Date | Commit | SHA |
|---|---|---|
| 2024-03-07 | Adding `safetensors` variant of this model (#2) | e063262 |
| 2024-02-22 | Added correct model to load (#5) | cfaa733 |
| 2024-02-02 | Update README.md | bba8780 |
| 2024-01-05 | Update README.md | 0f12b15 |
| 2024-01-05 | Update README.md | f711fc1 |
| 2023-12-13 | Update tokenizer_config.json | 2df081c |
| 2023-12-10 | Update tokenizer_config.json | e4d175e |
| 2023-11-29 | Update tokenizer_config.json | e04e040 |
| 2023-11-28 | Update tokenizer_config.json | c828ce4 |
| 2023-11-05 | Update tokenizer_config.json (#1) | 5bb36a3 |
| 2023-11-05 | Update generation_config.json | c527bd5 |
| 2023-11-05 | Update config.json | 70cbe98 |
| 2023-11-05 | Upload LICENSE | 0abf398 |
| 2023-11-05 | Delete LICENSE | 98151a2 |
| 2023-11-05 | Update README.md | 2a1fe24 |
| 2023-11-05 | Update config.json | 6cded73 |
| 2023-11-04 | Update tokenizer_config.json | 6687207 |
| 2023-11-04 | Update README.md | 6eec09c |
| 2023-11-03 | Update README.md | 06a98d3 |
| 2023-11-03 | Delete pytorch_model.bin.index.json | 9ea1283 |
| 2023-11-02 | Update README.md | 86c3cbf |
| 2023-11-02 | Update README.md | 7064d64 |
| 2023-11-01 | Update tokenizer_config.json | da53527 |
| 2023-11-01 | Update README.md | d9e1a4e |
| 2023-11-01 | update | 99f936e |
| 2023-10-29 | upload models | d4c4181 |
| 2023-10-29 | initial commit | 964a8d0 |
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 | 2026-10-07 | hn |
| DeepSeek V4 Flash 0731 Intelligence, Performance and Price Analysis | artificialanalysis.ai | 2026-07-31 | 2026-10-07 | hn |
| DeepSeek OCR | github.com | 2025-10-20 | 2026-10-07 | hn |
| The path to open-sourcing the DeepSeek inference engine | github.com | 2025-04-14 | 2026-10-07 | hn |
| DeepSeek Open Infra: Open-Sourcing 5 AI Repos in 5 Days | github.com | 2025-02-21 | 2026-10-07 | hn |
| OpenAI says it has evidence DeepSeek used its model to train competitor | ft.com | 2025-01-29 | 2026-10-07 | hn |
| DeepSeek releases Janus Pro, a text-to-image generator [pdf] | github.com | 2025-01-27 | 2026-10-07 | hn |
| DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via RL | arxiv.org | 2025-01-25 | 2026-10-07 | hn |
| DeepSeek-R1 | github.com | 2025-01-20 | 2026-10-07 | hn |
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.
