← CanIRunLocal · All hardware · All models
No. Qwen3-Coder 30B-A3B (MoE) does not fit on M2 8GB: Q4_K_M needs 20.4 GB and 5.4 GB is usable.
Hardware: M2 8GB · Model: Qwen3-Coder 30B-A3B (MoE)
M2 8GB has 8 GB of unified memory and 100 GB/s of memory bandwidth. M3 8GB has the same memory and bandwidth, so the fit numbers match; this page is M2 8GB. The checker leaves macOS a share of unified memory, so Ollama can use 5.4 GB. Qwen3-Coder 30B-A3B (MoE) (30.5B, 3.3B active, Alibaba) at Q4_K_M is a 19 GB download and needs 20.4 GB with headroom for about 8k tokens.
| Best quant | Q4_K_M |
|---|---|
| Download size | 19 GB |
| Memory needed | 20.4 GB |
| Usable fast memory | 5.4 GB |
| Fit | does not fit |
| Estimated speed | no estimate, it does not fit |
| Command | ollama run qwen3-coder:30b |
Smallest hardware that runs it: RTX 3060 12GB at Q4_K_M (partial offload (slower), 20.4 GB needed, 11.5 GB usable, about 18 tok/s (estimate)). Can a RTX 3060 12GB run Qwen3-Coder 30B-A3B (MoE)?
A smaller Alibaba model that fits this hardware: Qwen3.5 4B at Q4_K_M (fits in fast memory, 4.5 GB). Can a M2 8GB run Qwen3.5 4B?
Open M2 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