Up to date
deepseek-ai MIT out 21 months ago
70.6B parameters, text in, text out, 128K tokens of context. 1 provider serves it.
Verified 2026-10-25 Rank #126 in LLMs · score 94.9 method v1 Sources 3 Downloads 30d 37k · #404 of 619 tracked
Changed this week: 1 new quantized build on the Hub (71 in all).2026-10-24
Picked by rule from 37 tracked pieces: the lab's own post, the most shared, a field report, the latest.
Zyphra released ZAYA1-8B, a model that matches DeepSeek-R1 on math benchmarks while using less than 1 billion active parameters.
The 2 picks above, plus these 23. Top is the radar's score: discussion, source authority and the lab's own posts, fading with age.
Live hosted endpoints, cheapest first, USD per million tokens. Ties break on output price, then provider name.
| # | Cheapest live row | In /1M | Out /1M | Context | Quant | Seen |
|---|---|---|---|---|---|---|
| 1 | Featherless | — | — | — | — | Oct 25 |
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.
Served by 1 API provider; heavily run locally (71 quantized builds); a big base for builders (119 fine-tunes, adapters and merges).
Top Spaces running it: pliny-the-prompter/obliteratus ♥ 621 · hadadrjt/ai ♥ 86 · KBaba7/Quant ♥ 51 · ruslanmv/DeepSeek-R1-Chatbot ♥ 36
Weights only, an estimate: leave room for the KV cache. Method
About 42 GB at INT4, 85 GB at FP8, 169 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 (2025-01-20), amber triangles are 10 dated articles (each links to it), grey ticks are repo commits.
190 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 AIME 2024 · Reason through hard problems | 70 pass@1 | DeepSeek-R1-Distill-Llama-70B | 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.
Listed in LLMs
| Pipeline tag | text-generation |
|---|---|
| Library | transformers |
| Architectures | LlamaForCausalLM |
| Model type | llama |
| Dtype | bfloat16 |
| Params by dtype | BF16: 70,553,706,496 |
| Size band | XL |
| MoE | no |
| Context length | 131,072 (config.json max_position_embeddings) |
| Papers | arXiv:2501.12948 |
| License | MIT (mit) |
| 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-R1-Distill-Llama-70B: params × bytes/param × 1.2 overhead. KV cache and activations are extra. How this is computed.
| BF16 (2 bytes/param) | 169 GB · Multi-GPU node (<640 GB) |
|---|---|
| FP8 (1 byte/param) | 85 GB · Multi-GPU node (<640 GB) |
| INT4 (0.5 bytes/param) | 42 GB · Single high-end GPU (<80 GB) |
Weights only (params × bytes/param × 1.2 overhead); KV cache and activations extra.
quantized: 71finetune: 25merge: 37adapter: 57
| Date | Commit | SHA |
|---|---|---|
| 2025-02-24 | Update bib info | b1c0b44 |
| 2025-02-09 | Update tokenizer_config.json | 0d6d11a |
| 2025-02-01 | Update README.md | 008f3f3 |
| 2025-01-26 | Update README.md | 1772b07 |
| 2025-01-23 | Update README.md | b427a01 |
| 2025-01-22 | Update tokenizer_config.json | d0e68d7 |
| 2025-01-22 | Update tokenizer_config.json | a681c70 |
| 2025-01-21 | Add generation_config.json | 0aeb3b7 |
| 2025-01-21 | add library tag for better code snippets and tags (#3) | 76f6c0b |
| 2025-01-20 | Release DeepSeek-R1 | 07a264a |
| 2025-01-20 | Add files using upload-large-folder tool | 288e64a |
| 2025-01-20 | initial commit | 9ab39d5 |
Hosted endpoints observed for DeepSeek-R1-Distill-Llama-70B, sorted by input price (USD per million tokens). Each row names its observer and date; prices change daily, so check the source before quoting.
| Provider | Model ref | Context | Quant | $/M in | $/M out | tok/s | TTFT | Tools | Status | Observed |
|---|---|---|---|---|---|---|---|---|---|---|
| Featherless hf | deepseek-ai/DeepSeek-R1-Distill-Llama-70B | — | — | — | — | — | — | — | live | 2026-10-25 |
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 21:34 UTC · Providers: 2026-10-24 21:44 UTC · Articles: 2026-10-24 21:45 UTC · Summary: 2026-10-07 15:01 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.
