DeepSWE
No official DeepSWE mini-swe-agent row for this identity on the public board we fetched.
Context window on the 2026-08-19 OpenRouter row: 262,144 tokens.
Max completion tokens on that row: 262,144.
Input / output on that row: $0.05 / $0.20 per 1M tokens.
Architecture fields: text->text · Other.
Hugging Face id on that row: nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16.
NVIDIA Nemotron 3 Nano 30B A3B is a small language MoE model with highest compute efficiency and accuracy for developers to build specialized agentic AI systems.
When you want the 2025-12-14 catalog SKU, not a later rename.
No independent board lists this exact SKU as of 2026-08-19.
Closest benchmarked sibling: Nemotron 3 Ultra, 27.39% Vals Index on the vals.ai hero index board. That is a score for the sibling, not for this SKU.
Boards checked: DeepSWE official (2026-08-13), Artificial Analysis Intelligence Index, vals.ai hero index. Every card that does carry a row is on the coding leaderboard.
No official DeepSWE mini-swe-agent row for this identity on the public board we fetched.
No Intelligence Index integer fetched for this identity. Chip omitted.
We did not open a vals.ai card for this identity. Chip omitted.
Plus is $25/mo with $25 weekly hosted usage. The Mac app stays free with your own keys. Get Plus is not Download for Mac.
Official weights id on the 2026-08-19 OpenRouter row: nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16. Community GGUF is a quant, not a second Continuum card.
This is the model repo, not Download for Mac. Downloads and likes from the Hugging Face API on 2026-08-19.
usedStorage and the sum of .safetensors sizes can differ (LFS pointers, non-shard files, duplicate copies). Cited separately. Source: recursive tree API, 2026-08-19.
| Path | Bytes |
|---|---|
model-00001-of-00013.safetensors | 4,991,205,008 |
model-00002-of-00013.safetensors | 4,992,601,472 |
model-00003-of-00013.safetensors | 4,992,601,824 |
model-00004-of-00013.safetensors | 4,995,693,256 |
model-00005-of-00013.safetensors | 4,980,545,984 |
model-00006-of-00013.safetensors | 4,999,410,040 |
model-00007-of-00013.safetensors | 4,992,601,952 |
model-00008-of-00013.safetensors | 4,992,601,976 |
model-00009-of-00013.safetensors | 4,995,693,256 |
model-00010-of-00013.safetensors | 4,992,601,976 |
model-00011-of-00013.safetensors | 4,995,693,256 |
model-00012-of-00013.safetensors | 4,995,693,272 |
model-00013-of-00013.safetensors | 3,239,751,000 |
tokenizer.json | 17,077,485 |
model.safetensors.index.json | 613,296 |
accuracy_chart.png | 191,028 |
tokenizer_config.json | 188,049 |
modeling_nemotron_h.py | 83,779 |
README.md | 73,215 |
configuration_nemotron_h.py | 12,893 |
chat_template.jinja | 10,504 |
nemo-evaluator-launcher-configs/local_nvidia_nemotron_3_nano_30b_a3b.yaml | 4,242 |
notebook.ipynb | 3,206 |
explainability.md | 3,003 |
privacy.md | 2,296 |
bias.md | 2,276 |
safety.md | 2,094 |
config.json | 1,817 |
.gitattributes | 1,625 |
nano_v3_reasoning_parser.py | 798 |
special_tokens_map.json | 420 |
generation_config.json | 197 |
.eval_results/mmlu-pro.yaml | 158 |
.eval_results/gpqa.yaml | 153 |
.eval_results/hle.yaml | 148 |
All 35 files the tree API returned are listed: every one of the 13 safetensor shards plus 22 other files. Files tab: https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16/tree/main.
OpenRouter slug nvidia/nemotron-3-nano-30b-a3b on the 2026-08-19 catalog.
First party: https://build.nvidia.com/.
Not on the Continuum host list fetched 2026-08-19.
We list first-party and OpenRouter, plus Continuum only when the live public allowlist named the id. This is not a 15-host routing table.
OpenRouter 2026-08-19: $0.05 in / $0.20 out per 1M tokens. Context 262,144 in / 262,144 out.
No separate internal-reasoning price on that row.
| Claim | Source | As of |
|---|---|---|
| OpenRouter id nvidia/nemotron-3-nano-30b-a3b; context 262144; created 1765731275; $0.05 / $0.20 per 1M | OpenRouter /api/v1/models | 2026-08-19 |
| OpenRouter id nvidia/nemotron-3-nano-30b-a3b, context 262,144 | OpenRouter /api/v1/models | 2026-08-19 |
| HF downloads 1,000,729 | Hugging Face API nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 | 2026-08-19 |
| HF safetensors.total: 31,577,937,344 stored tensors; HF API usedStorage 63,174,529,404 bytes; created 2025-12-04T03:37:11.000Z; HF tensors F32 + BF16 | Hugging Face API nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 | 2026-08-19 |
| 13 safetensor shards; shard bytes 63,156,694,272; tree files 35 | Hugging Face tree API nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 | 2026-08-19 |
No other card in this cluster shares a published DeepSWE official row we can put next to this one. We will not compare on vendor-blog numbers.
Continue through NVIDIA's model family with Nemotron Nano 12B 2 VL (free).
Lab posts pick a harness, an effort, a split, and sometimes a private eval set. DeepSWE publishes the official mini-swe-agent row with cost, tokens, and steps. Scale SWE-bench Pro only counts when the public shared-harness board has a row we can fetch. A higher lab number is usually a different test, not a better one.
No Continuum hosted id is verified for this model, so this page does not invent a curl target. Use the first-party API or the OpenRouter slug nvidia/nemotron-3-nano-30b-a3b.