Can MacBook Pro M5 Max 36 GB run MiniCPM5 2B?
36 GB unified · 460 GB/s memory bandwidth · MiniCPM5 2B has 2.5B parameters.
Short answer
Yes, excellent for chat and acceptable or better for every workload we test.
Best quantization for chat: Q8_0 (2.5 GB of weights) on LM Studio. Generation: 80–140 tok/s, leaving about 25 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 | Excellent | Q8_0 | 80–140 tok/s | under 1 s | 8K | Details |
| Coding questionswith Continue | Comfortable | Q8_0 | 80–130 tok/s | ≈1 s | 16K | Details |
| Coding in a repositorywith Aider | Acceptable | Q8_0 | 65–110 tok/s | ≈3 s | 32K | Details |
| Agentic codingwith OpenCode | Acceptable | Q8_0 | 65–110 tok/s | ≈4 s | 32K | Details |
| Long documents (64K)with Open WebUI | Comfortable | Q8_0 | 45–75 tok/s | ≈15 s | 64K | Details |
Speeds are bandwidth-based estimates; no direct benchmark exists for this pair. “First reply” is the time to read the workload’s opening prompt. How we calculate
Other models for MacBook Pro M5 Max 36 GB
The best-rated models for chat on this machine.
- Qwen3.6 35B-A3B95–160 tok/sExcellent
- Gemma 4 26B-A4B65–110 tok/sExcellent
- LFM2.5 24B-A2B130–220 tok/sExcellent
- Qwen3.5 35B-A3B95–160 tok/sExcellent
- gpt-oss-20b80–130 tok/sExcellent
- GLM-4.7-Flash (30B-A3B)95–150 tok/sExcellent
Cheapest machines for MiniCPM5 2B
Hardware rated comfortable or better for chat, lowest price first.
Different tool, context size or workload?
These pages use typical settings. The full check models your exact setup.