← CanIRunLocal · All hardware · All models
Yes. Qwen3-VL 4B fits in fast memory on M3 8GB at Q4_K_M (4.5 GB needed, 5.4 GB usable), about 24 tok/s (estimate).
Hardware: M3 8GB · Model: Qwen3-VL 4B
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. Qwen3-VL 4B (4.44B, Alibaba) at Q4_K_M is a 3.3 GB download and needs 4.5 GB with headroom for about 8k tokens.
| Best quant | Q4_K_M |
|---|---|
| Download size | 3.3 GB |
| Memory needed | 4.5 GB |
| Usable fast memory | 5.4 GB |
| Fit | fits in fast memory |
| Estimated speed | ~24 tok/s (estimate) |
| Command | ollama run qwen3-vl:4b |
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