Nemotron 3 Nano Omni 30B A3B Reasoning
nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16
Released2026-04-28Size30B · 3B activeArchitecturehybrid linear attnLicensenvidia-open-model-agreementAA rank#60 of 75
Files and memory at 8K context
| Quant | File | Files | + KV + runtime | Smallest fit | Source |
|---|---|---|---|---|---|
| Q4_K_M lmstudio-community/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-GGUF | 22.83 GiB | 1 | unknown | 32 GB GPU (cache unknown) | HF files |
| Q8_0 unsloth/NVIDIA-Nemotron-3-Nano-Omni-30B-A3B-Reasoning-GGUF | 31.28 GiB | 1 | unknown | 48 GB GPU (cache unknown) | HF files |
| MLX 4-bit mlx-community/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-4bit | 18.29 GiB | 4 | unknown | 32 GB Mac (cache unknown) | HF files |
| MLX 8-bit mlx-community/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-8bit | 33.32 GiB | 8 | unknown | 48 GB Mac (cache unknown) | HF files |
No verified file: Q5_K_M, FP16. Sizes are exact file bytes (text weights; projectors listed separately). “+” = recurrent state or other terms unknown. Smallest fit adds 0.5 GiB spare; Macs use 75% of memory.
Quality
Artificial Analysis Intelligence Index
10.3 AA estimate
Variant: Nemotron 3 Nano Omni 30B A3B Reasoning · observed 2026-10-17 · source
Rank #60 of 75 researched 2026 models.
Arena text rating
Unknown
Scores describe the evaluated hosted variant, not each quantized file. AA and Arena are never averaged.
Reported speeds 0
No reported measurement yet. Submit one.
Community threads
- Please support MTP Hugging Face · 2026-06-21
- `modeling_nemotron_h.py` missing `supports_gradient_checkpointing = True` on `NemotronHPreTrainedModel` Hugging Face · 2026-05-13
Qualitative signals only; titles are not verified claims.