text model · Mistral · macOS
Can I run Mistral Small 3 24B on Apple M4 Pro (24GB)?
No. Mistral Small 3 24B needs ~16.3 GB even at Q4_K_M, but Apple M4 Pro (24GB) only has ~16 GB usable.
Needs ~16.3 GB even at Q4_K_M, but only ~16 GB is usable.
That figure is at a 4k context and moves about ±15% as context length changes.
The gap is about 0.3 GB: Mistral Small 3 24B needs roughly 16.3 GB at Q4_K_M and Apple M4 Pro (24GB) leaves only about 16 GB usable for a model. The lightest tracked hardware that runs Mistral Small 3 24B is the Nvidia GeForce RTX 4090 (24GB) at 24 GB. See Mistral Small 3 24B on Nvidia GeForce RTX 4090 (24GB).
- Q4_K_M needed
- ~16.3 GB
- Usable on device
- ~16 GB
- Device memory
- 24 GB
Which quant fits
- Parameters
- 24B
- Q4_K_M size
- 14.33 GB
- Q8_0 size
- 25.05 GB
- Context
- 128k
- Ollama tag
- mistral-small3.2:24b
- Memory
- 24 GB unified
- Usable for weights
- ~16 GB
- Power draw
- ~140 W
- Best runtime
- Ollama (MLX backend, preview) / MLX direct
What you can run instead
Run Mistral Small 3 24B on other hardware
FAQ
Can Apple M4 Pro (24GB) run Mistral Small 3 24B?
No. Mistral Small 3 24B needs ~16.3 GB even at Q4_K_M, but Apple M4 Pro (24GB) only has ~16 GB usable.
How much memory does Mistral Small 3 24B need?
Apple M4 Pro (24GB) does not have enough memory. At Q4_K_M the weights are ~14.33 GB; with KV cache and runtime overhead, budget ~16.3 GB at a 4k context.
What is the best tool to run Mistral Small 3 24B 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/mistral-small-3-24b/apple-m4-pro-24gb) Sources
- apple.com/newsroom/2024/10/apple-introduces-m4-pro-and-m4-max
- apple.com/newsroom/2024/10/new-macbook-pro-features-m4-family-of-chips-and-apple-intelligence
- developer.apple.com
- docs.mistral.ai
- github.com/ml-explore
- github.com/raullenchai
- huggingface.co
- lmarena.ai
- lmstudio.ai
- ollama.com/library/mistral-small3.2
- ollama.com/library/mistral-small3.2/tags
- support.apple.com/en-us/103253
- support.apple.com/en-us/121553
- support.apple.com/en-us/121555
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.