With 24 GB of VRAM, the Tesla P40 runs Gemma 3 12B IT at Q4_K_M entirely on the GPU with an 8K context (about 9.1 GB needed). At Q8_0 it fits entirely.
Q4_K_M · 8K context
The model needs about 9.1 GB and fits in the 23.3 GB available, with 14.2 GB to spare.
~9.1 GB (8.5 GB–9.6 GB) needed · estimate
Fits entirely in VRAM · 14.2 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 12B IT Q8_08K~14.1 GB · 20–26 tok/s estimate | Excellent |
|---|---|
| Gemma 3 12B IT Q6_K8K~11.4 GB · 25–33 tok/s estimate | Excellent |
| Gemma 3 12B IT Q5_K_M8K~10.2 GB · 28–37 tok/s estimate | Excellent |
| Gemma 3 12B IT Q4_K_M8K~9.1 GB · 31–42 tok/s estimate | Excellent |
| Gemma 3 12B IT IQ4_XS8K~8.3 GB · 34–47 tok/s estimate | Excellent |
| Gemma 3 12B IT Q3_K_M8K~7.8 GB · 37–50 tok/s estimate | Excellent |
Prices and links follow the market you choose.
NVIDIA
CompatibleRuns Gemma 3 12B IT Q4_K_M entirely in memory
AMD
ExcellentRuns Gemma 3 12B IT Q4_K_M entirely in memory
Unified memory PC
ExcellentRuns Gemma 3 12B IT Q4_K_M entirely in memory
No current offer imported for this market: the link opens a marketplace search.
