NVIDIA models: prices and the hardware each needs
52 models, 0 sold per token by 0 vendors. Vendors are in alphabetical order; the price is the cheapest list price among them, per million tokens.
| Model | Size | Sold per token by | From, input | Output | GPU memory |
|---|---|---|---|---|---|
| diffusiongemma-26B-A4B-it-NVFP4 | 25.82 B | not sold per token | 16.1 GB | ||
| Gemma-4-26B-A4B-NVFP4 | 25.81 B | not sold per token | 16.1 GB | ||
| Gemma-4-31B-IT-NVFP4 | 31.27 B | not sold per token | 19.5 GB | ||
| GLM-5.2-NVFP4 | 743.38 B | not sold per token | 464.6 GB | ||
| GLM-5.3-NVFP4 (nvidia) | 753.33 B | not sold per token | 470.8 GB | ||
| gpt-oss-120b-Eagle3-short-context | 0.79 B | not sold per token | 2 GB | ||
| gpt-oss-120b-Eagle3-v3 | 0.79 B | not sold per token | 2 GB | ||
| Kimi-K2-Thinking-NVFP4 | 1026.41 B | not sold per token | 641.5 GB | ||
| Kimi-K2.5-NVFP4 | 1026.88 B | not sold per token | 641.8 GB | ||
| Llama-3.1-8B-Instruct-FP8 | 8.03 B | not sold per token | 10 GB | ||
| Llama-3.1-Nemotron-70B-Instruct-HF | 70.55 B | not sold per token | 176.4 GB | ||
| Llama-3.1-Nemotron-Nano-8B-v1 | 8.03 B | not sold per token | 20.1 GB | ||
| Llama-3_3-Nemotron-Super-49B-v1 | 49.87 B | not sold per token | 124.7 GB | ||
| Llama-3_3-Nemotron-Super-49B-v1_5 | 49.87 B | not sold per token | 124.7 GB | ||
| Llama-3_3-Nemotron-Super-49B-v1_5-FP8 | 49.87 B | not sold per token | 62.3 GB | ||
| MiniMax-M2.5-NVFP4 | 228.69 B | not sold per token | 142.9 GB | ||
| Mistral-Medium-3.5-128B-NVFP4 | 127.7 B | not sold per token | 79.8 GB | ||
| Mistral-NeMo-Minitron-8B-Instruct | 8.41 B | not sold per token | 21 GB | ||
| Nemotron-3.5-Parse | 0.63 B | not sold per token | 3.1 GB | ||
| Nemotron-H-56B-Base-8K | 56.32 B | not sold per token | 140.8 GB | ||
| Nemotron-H-8B-Base-8K | 8.1 B | not sold per token | 20.2 GB | ||
| Nemotron-Labs-Diffusion-14B | 13.51 B | not sold per token | 33.8 GB | ||
| Nemotron-Labs-Diffusion-3B | 3.83 B | not sold per token | 9.6 GB | ||
| Nemotron-Labs-Diffusion-8B | 8.49 B | not sold per token | 21.2 GB | ||
| Nemotron-Labs-Diffusion-8B-Base | 8.49 B | not sold per token | 21.2 GB | ||
| NVIDIA-Nemotron-3-Nano-30B-A3B-Base-BF16 | 31.58 B | not sold per token | 78.9 GB | ||
| NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 | 31.58 B | not sold per token | 78.9 GB | ||
| NVIDIA-Nemotron-3-Nano-30B-A3B-FP8 | 31.58 B | not sold per token | 39.5 GB | ||
| NVIDIA-Nemotron-3-Nano-4B-BF16 | 3.97 B | not sold per token | 9.9 GB | ||
| NVIDIA-Nemotron-3-Nano-4B-FP8 | 3.97 B | not sold per token | 5 GB | ||
| NVIDIA-Nemotron-3-Super-120B-A12B-BF16 | 123.61 B | not sold per token | 309 GB | ||
| NVIDIA-Nemotron-3-Super-120B-A12B-FP8 | 123.61 B | not sold per token | 154.5 GB | ||
| NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4 | 123.61 B | not sold per token | 77.3 GB | ||
| NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16 | 560.52 B | not sold per token | 1401.3 GB | ||
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4 | 560.52 B | not sold per token | 350.3 GB | ||
| NVIDIA-Nemotron-3.5-Lightning-30B-A3B-Base-BF16 | 31.58 B | not sold per token | 78.9 GB | ||
| NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16 | 31.58 B | not sold per token | 78.9 GB | ||
| NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4 | 32.91 B | not sold per token | 20.6 GB | ||
| NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4-DSpark | 0.76 B | not sold per token | 1.9 GB | ||
| NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-NVFP4 | 65.77 B | not sold per token | 93.8 GB | ||
| NVIDIA-Nemotron-Nano-9B-v2 | 8.89 B | not sold per token | 22.2 GB | ||
| NVIDIA-Nemotron-Nano-9B-v2-FP8 | 8.89 B | not sold per token | 11.1 GB | ||
| Qwen2.5-VL-7B-Instruct-NVFP4 | 8.29 B | not sold per token | 5.2 GB | ||
| Qwen3-14B-FP8 (nvidia) | 14.77 B | not sold per token | 18.5 GB | ||
| Qwen3-14B-NVFP4 | 14.77 B | not sold per token | 9.2 GB | ||
| Qwen3-30B-A3B-NVFP4 | 30.53 B | not sold per token | 19.1 GB | ||
| Qwen3-8B-NVFP4 | 8.19 B | not sold per token | 5.1 GB | ||
| Qwen3.5-122B-A10B-NVFP4 | 122.56 B | not sold per token | 76.6 GB | ||
| Qwen3.5-397B-A17B-NVFP4 | 396.8 B | not sold per token | 248 GB | ||
| Qwen3.6-27B-NVFP4 | 27.36 B | not sold per token | 17.1 GB | ||
| Qwen3.6-35B-A3B-NVFP4 | 35.11 B | not sold per token | 21.9 GB | ||
| Qwen3.8-27B-NVFP4 | 27.36 B | not sold per token | 17.1 GB |