← CanIRunLocal · All hardware · All models
Yes. Mixtral 8x7B (MoE) fits in fast memory on Mac Studio M4 Max (40c GPU) 128GB at Q8_0 (51.8 GB needed, 96.0 GB usable), about 16 tok/s (estimate).
Hardware: Mac Studio M4 Max (40c GPU) 128GB · Model: Mixtral 8x7B (MoE)
Mac Studio M4 Max (40c GPU) 128GB has 128 GB of unified memory and 546 GB/s of memory bandwidth. M4 Max (40c GPU) 128GB has the same memory and bandwidth, so the fit numbers match; this page is Mac Studio M4 Max (40c GPU) 128GB. The checker leaves macOS a share of unified memory, so Ollama can use 96.0 GB. Mixtral 8x7B (MoE) (46.7B, 12.9B active, Mistral) at Q8_0 is a 50 GB download and needs 51.8 GB with headroom for about 8k tokens.
| Best quant | Q8_0 |
|---|---|
| Download size | 50 GB |
| Memory needed | 51.8 GB |
| Usable fast memory | 96.0 GB |
| Fit | fits in fast memory |
| Estimated speed | ~16 tok/s (estimate) |
| Command | ollama run mixtral:8x7b-instruct-v0.1-q8_0 |
Estimates, not benchmarks. Model sizes are ollama.com download sizes; memory needed adds headroom for ~8k tokens of context; speeds are rough figures from memory bandwidth. Data updated 2026-10-23.
A project by OnDevice Labs · llms.txt