← CanIRunLocal · All hardware · All models
Yes. North Mini Code 1.0 30B (MoE) fits in fast memory on M3 Max (40c GPU) 128GB at Q8_0 (34.1 GB needed, 96.0 GB usable), about 10 tok/s (estimate).
Hardware: M3 Max (40c GPU) 128GB · Model: North Mini Code 1.0 30B (MoE)
M3 Max (40c GPU) 128GB has 128 GB of unified memory and 400 GB/s of memory bandwidth. The checker leaves macOS a share of unified memory, so Ollama can use 96.0 GB. North Mini Code 1.0 30B (MoE) (30.5B, Cohere) at Q8_0 is a 32 GB download and needs 34.1 GB with headroom for about 8k tokens.
| Best quant | Q8_0 |
|---|---|
| Download size | 32 GB |
| Memory needed | 34.1 GB |
| Usable fast memory | 96.0 GB |
| Fit | fits in fast memory |
| Estimated speed | ~10 tok/s (estimate) |
| Command | ollama run north-mini-code-1.0: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