← CanIRunLocal · All hardware · All models
Yes. SmolLM2 360M fits in fast memory on M1 8GB at FP16 (1.3 GB needed, 5.4 GB usable), about 75 tok/s (estimate).
Hardware: M1 8GB · Model: SmolLM2 360M
M1 8GB has 8 GB of unified memory and 68 GB/s of memory bandwidth. The checker leaves macOS a share of unified memory, so Ollama can use 5.4 GB. SmolLM2 360M (0.362B, HuggingFace) at FP16 is a 0.73 GB download and needs 1.3 GB with headroom for about 8k tokens.
| Best quant | FP16 |
|---|---|
| Download size | 0.73 GB |
| Memory needed | 1.3 GB |
| Usable fast memory | 5.4 GB |
| Fit | fits in fast memory |
| Estimated speed | ~75 tok/s (estimate) |
| Command | ollama run smollm2:360m |
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