With 80 GB of VRAM, the H100 PCIe runs Gemma 3 27B IT at Q4_K_M entirely on the GPU with an 8K context (about 18.3 GB needed). At Q8_0 it fits entirely.
Q4_K_M · 8K context
The model needs about 18.3 GB and fits in the 77.6 GB available, with 59.3 GB to spare.
~18.3 GB (17.6 GB–19.1 GB) needed · estimate
Fits entirely in VRAM · 59.3 GB left
EstimateData updated 24 days agoSource: Run LLM Locally engine, Hugging Face config.json + model card
What makes this estimate less reliable
| Gemma 3 27B IT Q8_08K~30.2 GB · 44–62 tok/s estimate | Excellent |
|---|---|
| Gemma 3 27B IT Q6_K8K~23.8 GB · 54–78 tok/s estimate | Excellent |
| Gemma 3 27B IT Q5_K_M8K~21 GB · 60–89 tok/s estimate | Excellent |
| Gemma 3 27B IT Q4_K_M8K~18.3 GB · 68–101 tok/s estimate | Excellent |
| Gemma 3 27B IT IQ4_XS8K~16.6 GB · 73–111 tok/s estimate | Excellent |
| Gemma 3 27B IT Q3_K_M8K~15.3 GB · 78–120 tok/s estimate | Excellent |
Prices and links follow the market you choose.
AMD
CompatibleRuns Gemma 3 27B IT Q4_K_M entirely in memory
Unified memory PC
CompatibleRuns Gemma 3 27B IT Q4_K_M entirely in memory
No current offer imported for this market: the link opens a marketplace search.
