Can MacBook Pro M3 Max 96 GB run Mistral Small 3.2 (24B)?
96 GB unified · 300 GB/s memory bandwidth · Mistral Small 3.2 (24B) has 24B parameters.
Short answer
Yes, comfortable for chat; borderline for agentic coding.
Best quantization for chat: 5-bit (16 GB of weights) on LM Studio. Generation: 11–15 tok/s, leaving about 68 GB free for your other apps.
How it rates for each workload
Same model and machine, different jobs. Agents and long documents send far bigger prompts than chat, so they need much more speed and memory.
| Workload | Verdict | Quant | Generation | First reply | Context | |
|---|---|---|---|---|---|---|
| Chatwith Open WebUI | Comfortable | 5-bit | 11–15 tok/s | ≈5 s | 8K | Details |
| Coding questionswith Continue | Acceptable | 5-bit | 11–15 tok/s | ≈30 s | 16K | Details |
| Coding in a repositorywith Aider | Acceptable | 5-bit | 10–13 tok/s | ≈2 min | 32K | Details |
| Agentic codingwith OpenCode | Borderline | 5-bit | 9–13 tok/s | ≈3 min | 32K | Details |
| Long documents (64K)with Open WebUI | Borderline | 6-bit | 7–9 tok/s | ≈9 min | 64K | Details |
Speeds are estimates calibrated against measured benchmarks on similar hardware. “First reply” is the time to read the workload’s opening prompt. How we calculate
Get it running
Copy-paste commands for the 5-bit build with a 32K context. Ollama and llama.cpp download the file straight from Hugging Face.
ollama run hf.co/unsloth/Mistral-Small-3.2-24B-Instruct-2506-GGUF:Q5_K_M
Downloads 16.76 GB (Q5_K_M). Ollama's default context is small: set OLLAMA_CONTEXT_LENGTH=32768 before `ollama serve` for long prompts.
Other models for MacBook Pro M3 Max 96 GB
The best-rated models for chat on this machine.
- gpt-oss-120b50–65 tok/sExcellent
- Qwen3.6 35B-A3B55–75 tok/sExcellent
- Qwen3-Next 80B-A3B Instruct65–90 tok/sExcellent
- Gemma 4 26B-A4B45–60 tok/sExcellent
- Qwen3.5 35B-A3B55–75 tok/sExcellent
- LFM2.5 24B-A2B110–150 tok/sExcellent
Cheapest machines for Mistral Small 3.2 (24B)
Hardware rated comfortable or better for chat, lowest price first.
- Mac mini M4 Pro 24 GB$1,399 · 12–16 tok/sComfortable
- Desktop PC · Intel Arc Pro B60 24GB · 32 GB RAM$1,500 · 10–17 tok/sComfortable
- Desktop PC · Radeon RX 7900 XT · 32 GB RAM$1,550 · 30–45 tok/sExcellent
- Ryzen AI Max+ 395 mini PC / Framework Desktop · 64 GB$1,600 · 11–15 tok/sComfortable
- Desktop PC · Intel Arc Pro B60 24GB · 64 GB RAM$1,628 · 10–17 tok/sComfortable
- Mac mini M5 Pro 24 GB$1,699 · 11–18 tok/sComfortable
Same chip, other memory: 36 GB
Different tool, context size or workload?
These pages use typical settings. The full check models your exact setup.