Up to date
nvidia CC BY-NC 4.0 out 17 months ago
1.78B parameters, text in, text out. 1 provider serves it.
Verified 2026-10-25 Rank #773 in LLMs · score 71.1 method v1 Sources 3 Downloads 30d 1.2k · #590 of 619 tracked
Picked by rule from 25 tracked pieces: the lab's own post, the most shared, a field report, the latest.
NVIDIA released Nemotron 3 Ultra on June 4, 2026, as a 550 billion parameter hybrid Mamba-Attention Mixture-of-Experts model designed for long agentic runs.
The 1 pick above, plus these 24. 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; 22 quantized builds for local use.
Weights only, an estimate: leave room for the KV cache. Method
About 1.1 GB at INT4, 2.1 GB at FP8, 4.3 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 (2025-05-28), amber triangles are 10 dated articles (each links to it).
30 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.
Listed in LLMs
| Pipeline tag | text-generation |
|---|---|
| Library | transformers |
| Architectures | Qwen2ForCausalLM |
| Model type | qwen2 |
| Params by dtype | F32: 1,777,088,000 |
| Size band | S |
| MoE | no |
| Papers | arXiv:2505.24864, arXiv:2510.01180 |
| License | CC BY-NC 4.0 (cc-by-nc-4.0) |
| Hub snapshot | 2026-10-25 |
Weights-only memory for Nemotron-Research-Reasoning-Qwen-1.5B: params × bytes/param × 1.2 overhead. KV cache and activations are extra. How this is computed.
| BF16 (2 bytes/param) | 4.3 GB · Single GPU (<24 GB) |
|---|---|
| FP8 (1 byte/param) | 2.1 GB · Edge (<4 GB) |
| INT4 (0.5 bytes/param) | 1.1 GB · Edge (<4 GB) |
Weights only (params × bytes/param × 1.2 overhead); KV cache and activations extra.
Base model: deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
quantized: 22finetune: 8
Hosted endpoints observed for Nemotron-Research-Reasoning-Qwen-1.5B, 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/Nemotron-Research-Reasoning-Qwen-1.5B | — | — | — | — | — | — | — | 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 · Providers: 2026-10-24 21:44 UTC · Articles: 2026-10-24 21:46 UTC · Summary: 2026-10-14 14:08 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.
