Nemotron Nano models
6 Nemotron Nano models from NVIDIA on Hugging Face, from 4.0B to 13.2B parameters, published by NVIDIA in BF16, with a 128K-token context. The smallest official model, NVIDIA-Nemotron-Nano-9B-v2, needs about 19.9 GB of VRAM at its published precision; the cheapest live fit is RTX A5000 at $0.176/hr.
Part of the Nemotron series
Pick a size
One row per official Nemotron Nano size: the VRAM it needs at each precision, the cheapest GPU that holds it today, and the KV cache for a 32K-token context.
| Model | Parameters | Native VRAM | FP8 VRAM | INT4 VRAM | Live GPU fit (native) | Est. $/hr | KV cache at 32K |
|---|---|---|---|---|---|---|---|
| NVIDIA-Nemotron-Nano-9B-v2 | 8.9B | 19.9 GB | 9.9 GB | 5.0 GB | RTX A5000 | $0.176/hr | 0.50 GB |
| NVIDIA-Nemotron-Nano-12B-v2 | 12.3B | 27.5 GB | 13.8 GB | 6.9 GB | RTX A6000 | $0.363/hr | not published for this architecture |
VRAM is weights times a flat 1.2 overhead; the KV cache is a separate per-model figure at 16-bit, shown where the architecture is published. See the methodology.
Official models (2)
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| NVIDIA-Nemotron-Nano-9B-v2 | 8.9B | BF16 | 19.9 GB | RTX A5000 | $0.176/hr |
| NVIDIA-Nemotron-Nano-12B-v2 | 12.3B | BF16 | 27.5 GB | RTX A6000 | $0.363/hr |
Quantized versions (2)
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| NVIDIA-Nemotron-Nano-9B-v2-FP8 | 8.9B | F8_E4M3 | 9.9 GB | RTX 5060 Ti | $0.145/hr |
| NVIDIA-Nemotron-Nano-12B-v2-VL-FP8 | 13.2B | F8_E4M3 | 14.7 GB | RTX 5060 Ti | $0.145/hr |
Fine-tunes and community models (2)
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| lumi-4b | 4.0B | BF16 | 8.9 GB | RTX 3060 | $0.110/hr |
| lumi-4b | 4.0B | BF16 | 8.9 GB | RTX 3060 | $0.110/hr |
VRAM is for the precision the model is published in: the weights times a flat 1.2 overhead, with the KV cache not included. See the methodology. The fit shown is the lowest-priced single GPU type that holds the model at that precision, or the lowest-priced multi-GPU set (up to 8) when none does.
More from NVIDIA
- Parakeet (8 models)
- Nemotron 3 (19 models)
- Cosmos (7 models)
- nvidia (2 models)
- Nemotron Labs (5 models)
- Nemotron Speech (1 models)
- Nemotron Parse (1 models)
- Nemotron-H (3 models)
- Nemotron Cascade (1 models)
- Canary (2 models)
- Nemotron VoiceChat (1 models)