Nemotron Labs models
5 Nemotron Labs models from NVIDIA on Hugging Face, from 3.8B to 13.5B parameters, published by NVIDIA in BF16, with contexts from 4K to 256K tokens. The smallest official model, Nemotron-Labs-Diffusion-3B, needs about 8.6 GB of VRAM at its published precision; the cheapest live fit is RTX 3060 at $0.110/hr.
Part of the Nemotron series
Pick a size
One row per official Nemotron Labs 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 |
|---|---|---|---|---|---|---|---|
| Nemotron-Labs-Diffusion-3B | 3.8B | 8.6 GB | 4.3 GB | 2.1 GB | RTX 3060 | $0.110/hr | not published for this architecture |
| NVIDIA-Nemotron-Labs-Dory1.0-4B-BF16 | 4.0B | 8.9 GB | 4.4 GB | 2.2 GB | RTX 3060 | $0.110/hr | not published for this architecture |
| Nemotron-Labs-Diffusion-8B | 8.5B | 19.0 GB | 9.5 GB | 4.7 GB | RTX A5000 | $0.176/hr | not published for this architecture |
| Nemotron-Labs-Diffusion-14B | 13.5B | 30.2 GB | 15.1 GB | 7.5 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 (5)
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| Nemotron-Labs-Diffusion-3B | 3.8B | BF16 | 8.6 GB | RTX 3060 | $0.110/hr |
| NVIDIA-Nemotron-Labs-Dory1.0-4B-BF16 | 4.0B | BF16 | 8.9 GB | RTX 3060 | $0.110/hr |
| Nemotron-Labs-Diffusion-8B | 8.5B | BF16 | 19.0 GB | RTX A5000 | $0.176/hr |
| Nemotron-Labs-Diffusion-8B-Base | 8.5B | BF16 | 19.0 GB | RTX A5000 | $0.176/hr |
| Nemotron-Labs-Diffusion-14B | 13.5B | BF16 | 30.2 GB | RTX A6000 | $0.363/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)
- Nemotron Nano (6 models)
- nvidia (2 models)
- Nemotron Speech (1 models)
- Nemotron Parse (1 models)
- Nemotron-H (3 models)
- Nemotron Cascade (1 models)
- Canary (2 models)
- Nemotron VoiceChat (1 models)