With 24 GB of VRAM, the Tesla P40 runs Gemma 2 27B IT at Q4_K_M entirely on the GPU with an 8K context (about 19.6 GB needed). At Q8_0 it does not fit in VRAM.
Q4_K_M · 8K context
The model needs about 19.6 GB and fits in the 23.3 GB available, with 3.7 GB to spare.
~19.6 GB (18.9 GB–20.4 GB) needed · estimate
Fits entirely in VRAM · 3.7 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 27B IT Q8_08K~31.6 GB · 2–3.5 tok/s estimate | Possible but slow |
|---|---|
| Gemma 2 27B IT Q6_K8K~25.2 GB · 5–9 tok/s estimate | CPU/GPU offload |
| Gemma 2 27B IT Q5_K_M8K~22.3 GB · 13–17 tok/s estimate | Compatible |
| Gemma 2 27B IT Q4_K_M8K~19.6 GB · 15–19 tok/s estimate | Excellent |
| Gemma 2 27B IT IQ4_XS8K~17.8 GB · 16–21 tok/s estimate | Excellent |
| Gemma 2 27B IT Q3_K_M8K~16.5 GB · 18–23 tok/s estimate | Excellent |
Prices and links follow the market you choose.
AMD
ExcellentRuns Gemma 2 27B IT Q4_K_M entirely in memory
Unified memory PC
CompatibleRuns Gemma 2 27B IT Q4_K_M entirely in memory
Lowest memory tier
CompatibleRuns Gemma 2 27B IT Q4_K_M entirely in memory
No current offer imported for this market: the link opens a marketplace search.
