← CanIRunLocal · All hardware · All models
No. Devstral Small 2 24B does not fit on M4 Pro 24GB: Q4_K_M needs 16.8 GB and 16.1 GB is usable.
Hardware: M4 Pro 24GB · Model: Devstral Small 2 24B
M4 Pro 24GB has 24 GB of unified memory and 273 GB/s of memory bandwidth. The checker leaves macOS a share of unified memory, so Ollama can use 16.1 GB. Devstral Small 2 24B (24B, Mistral) at Q4_K_M is a 15 GB download and needs 16.8 GB with headroom for about 8k tokens.
| Best quant | Q4_K_M |
|---|---|
| Download size | 15 GB |
| Memory needed | 16.8 GB |
| Usable fast memory | 16.1 GB |
| Fit | does not fit |
| Estimated speed | no estimate, it does not fit |
| Command | ollama run devstral-small-2:24b |
Smallest hardware that runs it: RTX 3060 8GB at Q4_K_M (partial offload (slower), 16.8 GB needed, 7.5 GB usable, about 4 tok/s (estimate)). Can a RTX 3060 8GB run Devstral Small 2 24B?
A smaller Mistral model that fits this hardware: Mistral Small 24B at Q4_K_M (fits in fast memory, 15.8 GB). Can a M4 Pro 24GB run Mistral Small 24B?
Open M4 Pro 24GB 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