Mistral Nemo 12B Instruct at Q4_K_M needs about 9.4 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 9.4 GB but only 7.7 GB of VRAM is usable: 1.8 GB must be loaded into system RAM. It runs, 81% on the GPU, but more slowly.
~9.4 GB (9 GB–10 GB) needed · estimate
1.8 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
| Mistral Nemo 12B Instruct Q8_08K~14.9 GB · 2.5–5 tok/s estimate | CPU/GPU offload |
|---|---|
| Mistral Nemo 12B Instruct Q6_K8K~12 GB · 4–8 tok/s estimate | CPU/GPU offload |
| Mistral Nemo 12B Instruct Q5_K_M8K~10.7 GB · 5.5–11 tok/s estimate | CPU/GPU offload |
| Mistral Nemo 12B Instruct Q4_K_M8K~9.4 GB · 8.5–16 tok/s estimate | CPU/GPU offload |
| Mistral Nemo 12B Instruct IQ4_XS8K~8.7 GB · 12–21 tok/s estimate | CPU/GPU offload |
| Mistral Nemo 12B Instruct Q3_K_M8K~8.1 GB · 17–29 tok/s estimate | CPU/GPU offload |
Prices and links follow the market you choose.
NVIDIA
CompatibleRuns Mistral Nemo 12B Instruct Q4_K_M entirely in memory
AMD
ExcellentRuns Mistral Nemo 12B Instruct Q4_K_M entirely in memory
Unified memory PC
ExcellentRuns Mistral Nemo 12B Instruct Q4_K_M entirely in memory
Lowest memory tier
Compatible with limitsRuns Mistral Nemo 12B Instruct Q4_K_M entirely in memory
No current offer imported for this market: the link opens a marketplace search.
