← CanIRunLocal · All hardware · All models
Yes. Llama 3.1 8B fits in fast memory on M4 Max (40c GPU) 64GB at Q8_0 (9.5 GB needed, 48.0 GB usable), about 51 tok/s (estimate).
Hardware: M4 Max (40c GPU) 64GB · Model: Llama 3.1 8B
M4 Max (40c GPU) 64GB has 64 GB of unified memory and 546 GB/s of memory bandwidth. Mac Studio M4 Max (40c GPU) 64GB has the same memory and bandwidth, so the fit numbers match; this page is M4 Max (40c GPU) 64GB. The checker leaves macOS a share of unified memory, so Ollama can use 48.0 GB. Llama 3.1 8B (8.03B, Meta) at Q8_0 is a 8.5 GB download and needs 9.5 GB with headroom for about 8k tokens.
| Best quant | Q8_0 |
|---|---|
| Download size | 8.5 GB |
| Memory needed | 9.5 GB |
| Usable fast memory | 48.0 GB |
| Fit | fits in fast memory |
| Estimated speed | ~51 tok/s (estimate) |
| Command | ollama run llama3.1:8b-instruct-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