← CanIRunLocal · All hardware · All models
No. Qwen3.8 27B does not fit on M4 16GB: Default needs 20.3 GB and 10.7 GB is usable.
Hardware: M4 16GB · Model: Qwen3.8 27B
M4 16GB has 16 GB of unified memory and 120 GB/s of memory bandwidth. The checker leaves macOS a share of unified memory, so Ollama can use 10.7 GB. Qwen3.8 27B (27B, Alibaba) at Default is a 18 GB download and needs 20.3 GB with headroom for about 8k tokens.
| Best quant | Default |
|---|---|
| Download size | 18 GB |
| Memory needed | 20.3 GB |
| Usable fast memory | 10.7 GB |
| Fit | does not fit |
| Estimated speed | no estimate, it does not fit |
| Command | ollama run qwen3.8:27b |
Smallest hardware that runs it: RTX 3060 12GB at Default (partial offload (slower), 20.3 GB needed, 11.5 GB usable, about 4 tok/s (estimate)). Can a RTX 3060 12GB run Qwen3.8 27B?
A smaller Alibaba model that fits this hardware: Qwen 2.5 14B at Q4_K_M (fits in fast memory, 10.3 GB). Can a M4 16GB run Qwen 2.5 14B?
Open M4 16GB 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