Gemma 2 9B IT at Q4_K_M needs about 8.7 GB, more than the 8 GB of the RTX 4060: part of the model runs from system RAM, which slows generation. At Q3_K_M it does not fit in VRAM.
Q4_K_M · 8K context
The model needs about 8.7 GB but only 7.7 GB of VRAM is usable: 1.1 GB must be loaded into system RAM. It runs, 87% on the GPU, but more slowly.
~8.7 GB (8.2 GB–9.3 GB) needed · estimate
1.1 GB must be offloaded to system RAM
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 · 4–7.5 tok/s estimate | CPU/GPU offload |
|---|---|
| Gemma 2 9B IT Q6_K8K~10.5 GB · 6–12 tok/s estimate | CPU/GPU offload |
| Gemma 2 9B IT Q5_K_M8K~9.6 GB · 8.5–16 tok/s estimate | CPU/GPU offload |
| Gemma 2 9B IT Q4_K_M8K~8.7 GB · 12–22 tok/s estimate | CPU/GPU offload |
| Gemma 2 9B IT IQ4_XS8K~8.2 GB · 17–30 tok/s estimate | CPU/GPU offload |
| Gemma 2 9B IT Q3_K_M8K~7.8 GB · 24–41 tok/s estimate | CPU/GPU offload |
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.
