text model · EXAONE · macOS
Can I run EXAONE 4.0 32B on Apple M5 Pro (48GB)?
Yes. EXAONE 4.0 32B runs on Apple M5 Pro (48GB) at Q4_K_M (~20.2 GB of ~32 GB usable).
Runs at Q4_K_M using ~20.2 GB of ~32 GB usable.
That figure is at a 4k context and moves about ±15% as context length changes. Apple M5 Pro (48GB) leaves ~11.8 GB of headroom.
- Q4_K_M needed
- ~20.2 GB
- Usable on device
- ~32 GB
- Device memory
- 48 GB
- Best quant
- Q4_K_M
Which quant fits
Run it
Pick your tool. All 2 load the same Q4_K_M weights.
llama-cli -hf LGAI-EXAONE/EXAONE-4.0-32B-GGUF:Q4_K_M lms get LGAI-EXAONE/EXAONE-4.0-32B-GGUF How to run it
On macOS use LM Studio (Polished GUI, ships MLX on Apple Silicon, one-click model downloads.).
- Parameters
- 32B
- Q4_K_M size
- 18.02 GB
- Q8_0 size
- 31.67 GB
- Context
- 131k
- Memory
- 48 GB unified
- Usable for weights
- ~32 GB
- Best runtime
- MLX direct / Ollama (MLX backend)
You could also run
Run EXAONE 4.0 32B on other hardware
FAQ
Can Apple M5 Pro (48GB) run EXAONE 4.0 32B?
Yes. EXAONE 4.0 32B runs on Apple M5 Pro (48GB) at Q4_K_M (~20.2 GB of ~32 GB usable).
How much memory does EXAONE 4.0 32B need?
Apple M5 Pro (48GB) has room to spare. At Q4_K_M the weights are ~18.02 GB; with KV cache and runtime overhead, budget ~20.2 GB at a 4k context.
What is the best tool to run EXAONE 4.0 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.
Embed this
A live badge for your model card or README, updated as the data is. [](https://localmodel.run/can-i-run/exaone-4-32b/apple-m5-pro-48gb) Sources
Weights are measured from GGUF files; KV cache and overhead are computed, so totals can vary ~15% with context and runtime. Any tok/s is a bandwidth estimate. See methodology.