Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16
------ Total parameters 31B (Mamba2-Transformer hybrid MoE) Active parameters ~3B per token Max context 256k tokens Modalities (in) Video, Audio, Image, Text Modality (out) Text Reasoning mode On by default; toggle via enablethinking Best for Video+speech analysis, document intelligence (OCR/charts/long docs), GUI/agentic workflows, ASR Minimum GPU (BF16) 1× H100 80GB (single-GPU); 1× B200 / 1× H200 recommended Minim...
Params
33.0 B
Context
—
Downloads 30d
199 K
Likes
441
Download history
tracking started — chart appears after 7 days of snapshots (5 recorded)199 K downloads in the last 30 days
Can you run it?
Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.
| File | Quant | Size | Est. VRAM | Verdict on RTX 4090 · 24 GB |
|---|---|---|---|---|
| model.safetensors | bf16 | 66.0 GB | 78.1 GB | ❌ Won’t fit |
Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.
Use via API
via OpenRouter · USD per 1M tokens · synced 2026-10-24Free
input / 1M
Free
output / 1M
—
cached input / 1M
Free
1M in + 1M out
:free variant
Free in · Free out
- Context window
- 256,000 tokens
- Max output
- 65,536 tokens
- Providers
- —
- Cheapest provider
- —
- Best throughput
- —
- AA Intelligence / Coding / Agentic
- 10.3 / 13.8 / —
✓ Tool calling
✓ Reasoning
✗ Structured outputs
✓ Image input
✗ File input
✓ Audio input
✗ Prompt caching
Specifications
- Architecture
- NemotronH_Nano_Omni_Reasoning_V3
- Parameters
- 33.0 B
- Tensor type
- BF16
- Licence
- other
- First seen on the Hub
- 2026-04-20
- Training datasets
- nvidia/Nemotron-Image-Training-v3
- Added to our catalog
- 2026-10-20
Compare with any any-to-any model
Popular comparisons