← CanIRunLocal · All hardware · All models
No. LLaVA 1.6 7B does not fit on M3 8GB: Q4_K_M needs 6 GB and 5.4 GB is usable.
Hardware: M3 8GB · Model: LLaVA 1.6 7B
M3 8GB has 8 GB of unified memory and 100 GB/s of memory bandwidth. M2 8GB has the same memory and bandwidth, so the fit numbers match; this page is M3 8GB. The checker leaves macOS a share of unified memory, so Ollama can use 5.4 GB. LLaVA 1.6 7B (7.24B, LLaVA) at Q4_K_M is a 4.7 GB download and needs 6 GB with headroom for about 8k tokens.
| Best quant | Q4_K_M |
|---|---|
| Download size | 4.7 GB |
| Memory needed | 6 GB |
| Usable fast memory | 5.4 GB |
| Fit | does not fit |
| Estimated speed | no estimate, it does not fit |
| Command | ollama run llava:7b-v1.6-vicuna-q4_K_M |
Smallest hardware that runs it: RTX 3060 8GB at Q5_K_M (fits in fast memory, 6.7 GB needed, 7.5 GB usable, about 27 tok/s (estimate)). Can a RTX 3060 8GB run LLaVA 1.6 7B?
No smaller LLaVA model in this list fits M3 8GB.
Open M3 8GB in the checkerEstimates, 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