text model · Qwen2.5-Coder · macOS
Can I run Qwen2.5 Coder 32B on Apple M4 (24GB)?
No. Qwen2.5 Coder 32B needs ~20.7 GB even at Q4_K_M, but Apple M4 (24GB) only has ~16 GB usable.
Needs ~20.7 GB even at Q4_K_M, but only ~16 GB is usable.
- Q4_K_M needed
- ~20.7 GB
- Usable on device
- ~16 GB
- Device memory
- 24 GB
- Parameters
- 32B
- Q4_K_M size
- 18.49 GB
- Q8_0 size
- 32.43 GB
- Context
- 32k
- Ollama tag
- qwen2.5-coder:32b
- Memory
- 24 GB unified
- Usable for weights
- ~16 GB
- Best runtime
- Ollama (MLX backend, preview) / MLX direct
What you can run instead
Run Qwen2.5 Coder 32B on other hardware
FAQ
Can Apple M4 (24GB) run Qwen2.5 Coder 32B?
No. Qwen2.5 Coder 32B needs ~20.7 GB even at Q4_K_M, but Apple M4 (24GB) only has ~16 GB usable.
How much memory does Qwen2.5 Coder 32B need?
Apple M4 (24GB) does not have enough memory. At Q4_K_M the weights are ~18.49 GB; with KV cache and runtime overhead, budget ~20.7 GB at a 4k context.
What is the best tool to run Qwen2.5 Coder 32B on macOS?
LM Studio for a simple setup; mlx-lm for the most speed. vLLM is NOT a Mac tool, it is a CUDA/Linux serving engine. Unified memory is not a fixed VRAM slice; ~70% is usable for weights.
Sources
Memory figures are estimates. See methodology.