Up to date
nvidia NVIDIA Open Model License (nvidia-open-model-license) out 19 months ago
8.03B parameters, text in, text out, 128K tokens of context. 1 provider serves it.
Verified 2026-10-25 Rank #568 in LLMs · score 74.5 method v1 Sources 3 Downloads 30d 6.1k · #531 of 619 tracked
Picked by rule from 25 tracked pieces: the lab's own post, the most shared, a field report, the latest.
The 3 picks above, plus these 22. 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; 24 quantized builds for local use.
Top Spaces running it: ginigen-ai/smol-worldcup ♥ 59 · aimevzulari/Prompt_Uzmani ♥ 46 · build-small-hackathon/HearthNet ♥ 6 · build-small-hackathon/Scholar-Lens ♥ 3
Weights only, an estimate: leave room for the KV cache. Method
About 4.8 GB at INT4, 9.6 GB at FP8, 19 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 (2025-03-16), amber triangles are 10 dated articles (each links to it), grey ticks are repo commits.
50 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 2025 · Reason through hard problems | 0% pass@1 | Reasoning Off | model author | 2026-10-07 |
| author-reported AIME 2025 · Reason through hard problems | 47.1% pass@1 | Reasoning On | model author | 2026-10-07 |
| author-reported BFCL · Call tools and APIs | 63.9% percent | Reasoning Off | model author | 2026-10-07 |
| author-reported BFCL · Call tools and APIs | 63.6% percent | Reasoning On | model author | 2026-10-07 |
| author-reported GPQA Diamond · Reason through hard problems | 39.4% pass@1 | Reasoning Off | model author | 2026-10-07 |
| author-reported GPQA Diamond · Reason through hard problems | 54.1% pass@1 | Reasoning On | model author | 2026-10-07 |
| author-reported IFEval · Chat and follow instructions | 74.7% percent | Reasoning Off (Strict:Prompt) | model author | 2026-10-07 |
| author-reported IFEval · Chat and follow instructions | 82.1% percent | Reasoning Off (Strict:Instruction) | model author | 2026-10-07 |
| author-reported IFEval · Chat and follow instructions | 71.9% percent | Reasoning On (Strict:Prompt) | model author | 2026-10-07 |
| author-reported IFEval · Chat and follow instructions | 79.3% percent | Reasoning On (Strict:Instruction) | model author | 2026-10-07 |
| author-reported MATH-500 · Reason through hard problems | 36.6% pass@1 | Reasoning Off | model author | 2026-10-07 |
| author-reported MATH-500 · Reason through hard problems | 95.4% pass@1 | Reasoning On | model author | 2026-10-07 |
| author-reported MBPP · Write code with agents | 66.1% pass@1 | Reasoning Off | model author | 2026-10-07 |
| author-reported MBPP · Write code with agents | 84.6% pass@1 | Reasoning On | model author | 2026-10-07 |
| author-reported MT-Bench · Chat and follow instructions | 7.9 | Reasoning Off | model author | 2026-10-07 |
| author-reported MT-Bench · Chat and follow instructions | 8.1 | Reasoning On | model author | 2026-10-07 |
This dense decoder-only Transformer model is designed for tasks such as RAG, tool calling, and instruction-following.[1][2] The model is released under the NVIDIA Open Model License and supports a context length of up to 131,072 tokens.[3][4]
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: 8,030,261,248 |
| Size band | M |
| MoE | no |
| Context length | 131,072 (config.json max_position_embeddings) |
| Languages | en |
| Papers | arXiv:2505.00949, arXiv:2502.00203 |
| License | NVIDIA Open Model License (nvidia-open-model-license) (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 Llama-3.1-Nemotron-Nano-8B-v1: params × bytes/param × 1.2 overhead. KV cache and activations are extra. How this is computed.
| BF16 (2 bytes/param) | 19 GB · Single GPU (<24 GB) |
|---|---|
| FP8 (1 byte/param) | 9.6 GB · Single GPU (<24 GB) |
| INT4 (0.5 bytes/param) | 4.8 GB · Single GPU (<24 GB) |
Weights only (params × bytes/param × 1.2 overhead); KV cache and activations extra.
quantized: 24finetune: 9merge: 8adapter: 9
| Date | Commit | SHA |
|---|---|---|
| 2025-10-15 | Update README.md | 54641c1 |
| 2025-10-09 | Update README.md | 16011e5 |
| 2025-05-08 | Update README.md | a22e1c5 |
| 2025-05-05 | add link to technical report | 029ff12 |
| 2025-04-23 | Include expected behaviour for Reasoning ON | d10ce65 |
| 2025-03-16 | Initial commit | 42f62a4 |
| 2025-03-16 | initial commit | cecc65a |
Hosted endpoints observed for Llama-3.1-Nemotron-Nano-8B-v1, 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 | nvidia/Llama-3.1-Nemotron-Nano-8B-v1 | — | — | — | — | — | — | — | live | 2026-10-25 |
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.
