GPUs & Macs › NVIDIA Tesla V100 16GB
NVIDIA Tesla V100 16GB: local LLM speed
4 measured results for the NVIDIA Tesla V100 16GB.
Measured results
| Model | Generate tok/s | Prompt tok/s | Quant | Backend | Test | Source |
|---|---|---|---|---|---|---|
| Llama 3.2 1B Instruct | 258 | 9,419 | Q4_K_M | llamafile | LocalScore avg · n=2 | LocalScore LocalScore details |
| gpt-oss 20B | 118 | 3,527 | MXFP4 | CUDA FA on | tg128 | llama.cpp #15396 details |
| Llama 3.1 8B Instruct | 90.8 | 2,256 | Q4_K_M | llamafile | LocalScore avg | LocalScore details |
| Qwen2.5 14B Instruct | 53.0 | 1,184 | Q4_K_M | llamafile | LocalScore avg | LocalScore details |
What fits on the NVIDIA Tesla V100 16GB
Estimates for this chip are scaled from a measured run: Qwen2.5 14B Instruct Q4_K_M at 53.0 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 | UD-IQ3_XXS | 10.9 GB | 43.5 estimate |
| gemma-4-12B-it | Q8_0 | 12.7 GB | 37.6 estimate |
| Qwen3.5-9B | Q8_0 | 9.5 GB | 50.0 estimate |
| Qwen3.5-4B | Q8_0 | 4.5 GB | 106 estimate |
| Qwen3.6-35B-A3B | UD-IQ3_XXS | 13.2 GB | 210 estimate |
| gemma-4-26B-A4B-it | UD-IQ4_XS | 13.6 GB | 114 estimate |
| MiMo-V2.6-Distill-Qwen-9B | Q8_0 | 9.5 GB | 49.9 estimate |
| gemma-4-E4B-it | Q8_0 | 8.2 GB | 58.1 estimate |
| Muse-Glimmer-30B | UD-IQ3_XXS | 13.1 GB | 36.3 estimate |
| Qwen3-4B | Q8_0 | 4.3 GB | 111 estimate |
| gemma-4-31B-it | UD-IQ3_XXS | 11.8 GB | 40.2 estimate |
| gemma-4-12B-it-qat-q4_0-unquantized | UD-Q4_K_XL | 6.7 GB | 70.9 estimate |
| gemma-3-1b-it | Q8_0 | 1.1 GB | 397 estimate |
| gemma-4-E2B-it | Q8_0 | 5.0 GB | 95.8 estimate |
Similar hardware
NVIDIA Tesla P100 · NVIDIA Tesla T4 · NVIDIA Tesla K80 · NVIDIA A30 · NVIDIA Tesla P40 · NVIDIA Tesla M40 · NVIDIA Tesla P4 · NVIDIA L4