← CanIRunLocal · All hardware · All models
No. Mixtral 8x7B (MoE) does not fit on M2 16GB: Q4_K_M needs 29.8 GB and 10.7 GB is usable.
Hardware: M2 16GB · Model: Mixtral 8x7B (MoE)
M2 16GB has 16 GB of unified memory and 100 GB/s of memory bandwidth. M3 16GB has the same memory and bandwidth, so the fit numbers match; this page is M2 16GB. The checker leaves macOS a share of unified memory, so Ollama can use 10.7 GB. Mixtral 8x7B (MoE) (46.7B, 12.9B active, Mistral) at Q4_K_M is a 28 GB download and needs 29.8 GB with headroom for about 8k tokens.
| Best quant | Q4_K_M |
|---|---|
| Download size | 28 GB |
| Memory needed | 29.8 GB |
| Usable fast memory | 10.7 GB |
| Fit | does not fit |
| Estimated speed | no estimate, it does not fit |
| Command | ollama run mixtral:8x7b-instruct-v0.1-q4_K_M |
Smallest hardware that runs it: RTX 3090 24GB at Q4_K_M (partial offload (slower), 29.8 GB needed, 23.5 GB usable, about 10 tok/s (estimate)). Can a RTX 3090 24GB run Mixtral 8x7B (MoE)?
A smaller Mistral model that fits this hardware: Ministral 3 14B at Q4_K_M (fits in fast memory, 10.7 GB). Can a M2 16GB run Ministral 3 14B?
Open M2 16GB in the checkerEstimates, 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