← CanIRunLocal · All hardware · All models
Yes. LLaVA 1.6 7B fits in fast memory on M2 Max (38c GPU) 96GB at Q8_0 (9.1 GB needed, 72.0 GB usable), about 41 tok/s (estimate).
Hardware: M2 Max (38c GPU) 96GB · Model: LLaVA 1.6 7B
M2 Max (38c GPU) 96GB has 96 GB of unified memory and 400 GB/s of memory bandwidth. The checker leaves macOS a share of unified memory, so Ollama can use 72.0 GB. LLaVA 1.6 7B (7.24B, LLaVA) at Q8_0 is a 7.8 GB download and needs 9.1 GB with headroom for about 8k tokens.
| Best quant | Q8_0 |
|---|---|
| Download size | 7.8 GB |
| Memory needed | 9.1 GB |
| Usable fast memory | 72.0 GB |
| Fit | fits in fast memory |
| Estimated speed | ~41 tok/s (estimate) |
| Command | ollama run llava:7b-v1.6-vicuna-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