With 80 GB of VRAM, the H100 PCIe runs Gemma 2 9B IT at Q4_K_M entirely on the GPU with an 8K context (about 8.7 GB needed). At Q8_0 it fits entirely.
Q4_K_M · 8K context
The model needs about 8.7 GB and fits in the 77.6 GB available, with 68.9 GB to spare.
~8.7 GB (8.2 GB–9.3 GB) needed · estimate
Fits entirely in VRAM · 68.9 GB left
EstimateData updated 24 days agoSource: Run LLM Locally engine, Hugging Face config.json + model card
What makes this estimate less reliable
| Gemma 2 9B IT Q8_08K~12.7 GB · 105–158 tok/s estimate | Excellent |
|---|---|
| Gemma 2 9B IT Q6_K8K~10.5 GB · 123–192 tok/s estimate | Excellent |
| Gemma 2 9B IT Q5_K_M8K~9.6 GB · 133–211 tok/s estimate | Excellent |
| Gemma 2 9B IT Q4_K_M8K~8.7 GB · 144–233 tok/s estimate | Excellent |
| Gemma 2 9B IT IQ4_XS8K~8.2 GB · 153–250 tok/s estimate | Excellent |
| Gemma 2 9B IT Q3_K_M8K~7.8 GB · 159–264 tok/s estimate | Excellent |
Prices and links follow the market you choose.
NVIDIA
CompatibleRuns Gemma 2 9B IT Q4_K_M entirely in memory
AMD
ExcellentRuns Gemma 2 9B IT Q4_K_M entirely in memory
Unified memory PC
ExcellentRuns Gemma 2 9B IT Q4_K_M entirely in memory
No current offer imported for this market: the link opens a marketplace search.
