← CanIRunLocal · All hardware · All models
No. Hy-Memory 30B-A3B (MoE, memory) does not fit on M4 24GB: Q4_K_M needs 19.6 GB and 16.1 GB is usable.
Hardware: M4 24GB · Model: Hy-Memory 30B-A3B (MoE, memory)
M4 24GB has 24 GB of unified memory and 120 GB/s of memory bandwidth. The checker leaves macOS a share of unified memory, so Ollama can use 16.1 GB. Hy-Memory 30B-A3B (MoE, memory) (30.06B, 3B active, Tencent) at Q4_K_M is a 18.24 GB download and needs 19.6 GB with headroom for about 8k tokens.
| Best quant | Q4_K_M |
|---|---|
| Download size | 18.24 GB |
| Memory needed | 19.6 GB |
| Usable fast memory | 16.1 GB |
| Fit | does not fit |
| Estimated speed | no estimate, it does not fit |
| Command | ollama run hf.co/tencent/Hy-Memory-30B-A3B-GGUF:Q4_K_M |
Smallest hardware that runs it: RTX 3060 12GB at Q4_K_M (partial offload (slower), 19.6 GB needed, 11.5 GB usable, about 21 tok/s (estimate)). Can a RTX 3060 12GB run Hy-Memory 30B-A3B (MoE, memory)?
No smaller Tencent model in this list fits M4 24GB.
Open M4 24GB 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