DeepSWE
No official DeepSWE mini-swe-agent row for this identity on the public board we fetched.
NVIDIA Nemotron Nano 2 VL is a 12-billion-parameter open multimodal reasoning model designed for video understanding and document intelligence. It introduces a hybrid Transformer-Mamba architecture, combining transformer-level accuracy with Mamba’s...
Context window on the 2026-08-19 OpenRouter row: 128,000 tokens.
Max completion tokens on that row: 128,000.
Input / output on that row: $0 / $0 per 1M tokens.
Architecture fields: text+image+video->text · Other.
Hugging Face id on that row: nvidia/NVIDIA-Nemotron-Nano-12B-v2-VL-BF16.
NVIDIA Nemotron Nano 2 VL is a 12-billion-parameter open multimodal reasoning model designed for video understanding and document intelligence.
When you want the 2025-10-28 catalog SKU, not a later rename.
No official DeepSWE mini-swe-agent row for this identity on the public board we fetched.
We did not open a vals.ai card for this identity. Chip omitted.
Ranked view: Best coding models: the independent leaderboard puts this row and every other card that carries an independent coding score on one board, with the confidence intervals left visible.
Copied from AA or vals HTML we opened. 0.0% placeholder bars are omitted. Do not average these into the hero tiles, and do not invent CI, $/task, or steps for Artificial Analysis.
| Bench | Printed | Note | Source | URL | As of |
|---|---|---|---|---|---|
| SciCode | 17.6% | Printed on the AA Intelligence Evaluations grid for NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning). Not a DeepSWE chip. | Artificial Analysis NVIDIA Nemotron Nano 12B v2 VL | source | 2026-08-19 |
| Humanity's Last Exam | 4.3% | Printed on the AA Intelligence Evaluations grid for NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning). Not a DeepSWE chip. | Artificial Analysis NVIDIA Nemotron Nano 12B v2 VL | source | 2026-08-19 |
| GPQA Diamond | 43.9% | Printed on the AA Intelligence Evaluations grid for NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning). Not a DeepSWE chip. | Artificial Analysis NVIDIA Nemotron Nano 12B v2 VL | source | 2026-08-19 |
| AA-Omniscience Accuracy | 11.9% | Printed on the AA Intelligence Evaluations grid for NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning). Not a DeepSWE chip. | Artificial Analysis NVIDIA Nemotron Nano 12B v2 VL | source | 2026-08-19 |
| AA-LCR | 19.7% | Printed on the AA Intelligence Evaluations grid for NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning). Not a DeepSWE chip. | Artificial Analysis NVIDIA Nemotron Nano 12B v2 VL | source | 2026-08-19 |
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-Nano-12B-v2-VL-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-00007.safetensors | 3,831,944,248 |
model-00002-of-00007.safetensors | 3,908,097,776 |
model-00003-of-00007.safetensors | 3,908,097,808 |
model-00004-of-00007.safetensors | 3,824,190,384 |
model-00005-of-00007.safetensors | 3,908,097,808 |
model-00006-of-00007.safetensors | 3,908,097,808 |
model-00007-of-00007.safetensors | 3,075,291,960 |
tokenizer.json | 17,079,976 |
images/demo.mp4 | 7,333,182 |
images/demo_frames/frame_0000.jpg | 532,176 |
images/demo_frames/frame_0001.jpg | 525,666 |
images/demo_frames/frame_0002.jpg | 522,853 |
images/demo_frames/frame_0003.jpg | 510,824 |
images/demo_frames/frame_0004.jpg | 494,798 |
images/demo_frames/frame_0006.jpg | 466,415 |
images/demo_frames/frame_0007.jpg | 451,954 |
images/demo_frames/frame_0008.jpg | 446,495 |
images/demo_frames/frame_0009.jpg | 442,849 |
images/demo_frames/frame_0005.jpg | 435,068 |
images/demo_frames/frame_0014.jpg | 425,102 |
images/demo_frames/frame_0011.jpg | 399,758 |
images/demo_frames/frame_0010.jpg | 399,499 |
images/demo_frames/frame_0012.jpg | 374,855 |
images/demo_frames/frame_0013.jpg | 361,900 |
images/tech.png | 222,054 |
tokenizer_config.json | 185,845 |
images/table.png | 131,014 |
modeling_nemotron_h.py | 78,570 |
model.safetensors.index.json | 72,736 |
README.md | 20,007 |
images/example1a.jpeg | 14,890 |
Showing the first 7 of 7 safetensor shards, plus 24 other files. The snapshot was capped at 7 shards when the tree API was read on 2026-08-19, so the remaining 0 are on the Files tab, not on this page. Totals above are the full tree API sum, not this slice. Byte sizes are Hub tree API size fields, never invented.
OpenRouter slug nvidia/nemotron-nano-12b-v2-vl:free on the 2026-08-19 catalog.
First party: https://build.nvidia.com/.
Not on the Continuum host list fetched 2026-08-19.
not on the host list
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 in / $0 out per 1M tokens. Context 128,000 in / 128,000 out.
No separate internal-reasoning price on that row.
| Claim | Source | As of |
|---|---|---|
| OpenRouter id nvidia/nemotron-nano-12b-v2-vl:free; context 128000; created 1761675565; $0 / $0 per 1M | OpenRouter /api/v1/models | 2026-08-19 |
| AA Intelligence Index 4; 5 printed Index benches | Artificial Analysis model page | 2026-08-19 |
| OpenRouter id nvidia/nemotron-nano-12b-v2-vl:free, context 128,000 | OpenRouter /api/v1/models | 2026-08-19 |
| HF downloads 120,675 | Hugging Face API nvidia/NVIDIA-Nemotron-Nano-12B-v2-VL-BF16 | 2026-08-19 |
| HF safetensors.total: 13,181,860,358 stored tensors; HF API usedStorage 26,400,962,337 bytes; created 2025-10-21T18:11:05.000Z; HF tensors F32 + BF16 | Hugging Face API nvidia/NVIDIA-Nemotron-Nano-12B-v2-VL-BF16 | 2026-08-19 |
| 7 safetensor shards; shard bytes 26,363,817,792; tree files 54 | Hugging Face tree API nvidia/NVIDIA-Nemotron-Nano-12B-v2-VL-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 9B V2 (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-nano-12b-v2-vl:free.