← CanIRunLocal · All hardware · All models
Yes. Code Llama 7B fits in fast memory on M3 Max (40c GPU) 128GB at Q8_0 (8.1 GB needed, 96.0 GB usable), about 44 tok/s (estimate).
Hardware: M3 Max (40c GPU) 128GB · Model: Code Llama 7B
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. Code Llama 7B (6.74B, Meta) at Q8_0 is a 7.2 GB download and needs 8.1 GB with headroom for about 8k tokens.
| Best quant | Q8_0 |
|---|---|
| Download size | 7.2 GB |
| Memory needed | 8.1 GB |
| Usable fast memory | 96.0 GB |
| Fit | fits in fast memory |
| Estimated speed | ~44 tok/s (estimate) |
| Command | ollama run codellama:7b-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