can it run
Yes, but close to the edge. 40GB against a 33GB working set: it runs, with little room for long context windows or other processes.
| model file | 26GB (GGUF Q4_K_M) |
| minimum memory | 33GB working set |
| this machine | 40GB HBM2e, 1.55 TB/s |
| params | 8x7B MoE |
| license | apache-2.0 |
| price | $5900 |
easy run: ollama pull mixtral:8x7b
runs with: ollama · llama.cpp · koboldcpp · lm studio
→ Mac mini M5 Pro (64GB) — cheapest machine that runs it ($1669)
→ ASUS ExpertCenter Pro ET900N G3 (GB300) — this model on the biggest machine
NVIDIA (used market) ↗ · Amazon ↗