Gemma 2 27B IT at Q4_K_M needs about 19.7 GB, more than the 20 GB of the RX 7900 XT: part of the model runs from system RAM, which slows generation. At Q3_K_M it fits entirely.
Q4_K_M · 8K context
The model needs about 19.7 GB but only 19.4 GB of VRAM is usable: 0.3 GB must be loaded into system RAM. It runs, 99% on the GPU, but more slowly.
~19.7 GB (18.9 GB–20.5 GB) needed · estimate
0.3 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 27B IT Q8_08K~31.7 GB · 1.6–3 tok/s estimate | Possible but slow |
|---|---|
| Gemma 2 27B IT Q6_K8K~25.2 GB · 3–6 tok/s estimate | CPU/GPU offload |
| Gemma 2 27B IT Q5_K_M8K~22.4 GB · 5.5–11 tok/s estimate | CPU/GPU offload |
| Gemma 2 27B IT Q4_K_M8K~19.7 GB · 18–32 tok/s estimate | CPU/GPU offload |
| Gemma 2 27B IT IQ4_XS8K~17.9 GB · 31–44 tok/s estimate | Compatible |
| Gemma 2 27B IT Q3_K_M8K~16.5 GB · 33–47 tok/s estimate | Compatible |
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.
