← CanIRunLocal · All hardware · All models
No. GLM-4.7-Flash 30B-A3B (MoE) does not fit on M4 16GB: Q4_K_M needs 20.4 GB and 10.7 GB is usable.
Hardware: M4 16GB · Model: GLM-4.7-Flash 30B-A3B (MoE)
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. GLM-4.7-Flash 30B-A3B (MoE) (31.2B, 3B active, Z.ai) 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 | 10.7 GB |
| Fit | does not fit |
| Estimated speed | no estimate, it does not fit |
| Command | ollama run glm-4.7-flash:latest |
Smallest hardware that runs it: RTX 3060 12GB at Q4_K_M (partial offload (slower), 20.4 GB needed, 11.5 GB usable, about 20 tok/s (estimate)). Can a RTX 3060 12GB run GLM-4.7-Flash 30B-A3B (MoE)?
A smaller Z.ai model that fits this hardware: GLM-OCR 0.9B at BF16 (fits in fast memory, 3.7 GB). Can a M4 16GB run GLM-OCR 0.9B?
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