With 10 GB of VRAM, the RTX 3080 runs Granite 4.2 8B at Q4_K_M entirely on the GPU with an 8K context (about 7.3 GB needed). At Q8_0 it does not fit in VRAM.
Q4_K_M · 8K context
The model needs about 7.3 GB and fits in the 9.7 GB available, with 2.4 GB to spare.
~7.3 GB (6.9 GB–7.7 GB) needed · estimate
Fits entirely in VRAM · 2.4 GB left
EstimateData updated 40 days agoSource: Run LLM Locally engine, Hugging Face config.json + model card
What makes this estimate less reliable
| Granite 4.2 8B Q8_08K~11.2 GB · 11–21 tok/s estimate | CPU/GPU offload |
|---|---|
| Granite 4.2 8B Q6_K8K~9.1 GB · 63–88 tok/s estimate | Compatible |
| Granite 4.2 8B Q5_K_M8K~8.2 GB · 70–100 tok/s estimate | Excellent |
| Granite 4.2 8B Q4_K_M8K~7.3 GB · 79–113 tok/s estimate | Excellent |
| Granite 4.2 8B IQ4_XS8K~6.8 GB · 84–122 tok/s estimate | Excellent |
| Granite 4.2 8B Q3_K_M8K~6.3 GB · 91–134 tok/s estimate | Excellent |
Prices and links follow the market you choose.
10 GB GDDR6X · 760 GB/s · 320 W
ExcellentRuns Granite 4.2 8B Q4_K_M entirely in memory
No current offer imported for this market: the link opens a marketplace search.
