Mixtral 8x7B Instruct at Q4_K_M needs about 27.6 GB, more than the 16 GB of the RX 9070 XT: 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 27.6 GB but only 15.5 GB of VRAM is usable: 12 GB must be loaded into system RAM. It runs, 56% on the GPU, but more slowly.
~27.6 GB (26.8 GB–28.4 GB) needed · estimate
12 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
| Mixtral 8x7B Instruct Q8_08K~50.2 GB · 1.9–3.5 tok/s estimate | Possible but slow |
|---|---|
| Mixtral 8x7B Instruct Q6_K8K~39.2 GB · 3–5.5 tok/s estimate | Possible but slow |
| Mixtral 8x7B Instruct Q5_K_M8K~33.2 GB · 3.5–7 tok/s estimate | Possible but slow |
| Mixtral 8x7B Instruct Q4_K_M8K~27.6 GB · 5–10 tok/s estimate | CPU/GPU offload |
| Mixtral 8x7B Instruct IQ4_XS8K~27.2 GB · 5.5–11 tok/s estimate | CPU/GPU offload |
| Mixtral 8x7B Instruct Q3_K_M8K~21.6 GB · 9–18 tok/s estimate | CPU/GPU offload |
Prices and links follow the market you choose.
NVIDIA
CompatibleRuns Mixtral 8x7B Instruct Q4_K_M entirely in memory
AMD
ExcellentRuns Mixtral 8x7B Instruct Q4_K_M entirely in memory
Apple Silicon
ExcellentRuns Mixtral 8x7B Instruct Q4_K_M entirely in memory
Unified memory PC
ExcellentRuns Mixtral 8x7B Instruct Q4_K_M entirely in memory
No current offer imported for this market: the link opens a marketplace search.
