H100 80GB vs RTX 4060 Ti 16GB
For running local LLMs · 9 reports across 5 models
Highest reported generation speed by model family
These maxima come from different community setups. Model size, quantization, GPU count, offloading and concurrency may differ. They do not establish which GPU is faster for the same workload. Check the comparison conditions →
| Model | H100 80GB | RTX 4060 Ti 16GB |
|---|---|---|
| Qwen3.8up to 2400B | — | 32.5n=4 |
| DeepSeek V4 Flashup to 285B | 193.0n=1 | 7.4n=1 |
| Gemma 4up to 31B | 125.3n=1 | — |
| Qwen3.5up to 122B | —n=1 | — |
| Qwen3.6up to 35B | 45.0n=1 | — |