GPUs & Macs › NVIDIA H100 PCIe
NVIDIA H100 PCIe: local LLM speed
3 measured results for the NVIDIA H100 PCIe.
Measured results
| Model | Generate tok/s | Prompt tok/s | Quant | Backend | Test | Source |
|---|---|---|---|---|---|---|
| Llama 3.2 1B Instruct | 335 | 18,590 | Q4_K_M | llamafile | LocalScore avg | LocalScore details |
| Llama 3.1 8B Instruct | 120 | 5,202 | Q4_K_M | llamafile | LocalScore avg | LocalScore details |
| Qwen2.5 14B Instruct | 72.2 | 2,973 | Q4_K_M | llamafile | LocalScore avg | LocalScore details |
What fits on the NVIDIA H100 PCIe
Estimates for this chip are scaled from a measured run: Qwen2.5 14B Instruct Q4_K_M at 72.2 tok/s (llamafile, source). Fit assumes the whole model in GPU memory with ~8K context.
| Model | Best quant that fits | File | Expected tok/s |
|---|---|---|---|
| Qwen3.8-27B | Q8_0 | 29.0 GB | 22.3 estimate |
| gemma-4-12B-it | Q8_0 | 12.7 GB | 51.2 estimate |
| Qwen3.5-9B | Q8_0 | 9.5 GB | 68.1 estimate |
| Qwen3.5-4B | Q8_0 | 4.5 GB | 145 estimate |
| Qwen3.6-35B-A3B | Q8_0 | 36.9 GB | 103 estimate |
| Qwen3.8-Flash-Next | UD-IQ1_M | 74.5 GB | 8.7 estimate |
| gemma-4-26B-A4B-it | Q8_0 | 26.9 GB | 78.5 estimate |
| MiMo-V2.6-Distill-Qwen-9B | Q8_0 | 9.5 GB | 68.0 estimate |
| gemma-4-E4B-it | Q8_0 | 8.2 GB | 79.2 estimate |
| Muse-Glimmer-30B | Q8_0 | 29.6 GB | 21.9 estimate |
| Qwen3-4B | Q8_0 | 4.3 GB | 152 estimate |
| gemma-4-31B-it | Q8_0 | 32.6 GB | 19.9 estimate |
| gemma-4-26B-A4B-it-qat-q4_0-unquantized | UD-Q4_K_XL | 14.2 GB | 148 estimate |
| gemma-4-12B-it-qat-q4_0-unquantized | UD-Q4_K_XL | 6.7 GB | 96.6 estimate |
Similar hardware
NVIDIA H100 SXM · NVIDIA A100 80GB PCIe · NVIDIA A100 80GB SXM · NVIDIA L40 · NVIDIA A40 · NVIDIA L40S · NVIDIA Tesla V100 32GB · NVIDIA A30