M1 Pro 32GB vs M2 Max 32GB for local LLMs
2 reports on the M1 Pro 32GB and 2 on the M2 Max 32GB
Which is faster for local LLMs?
On Qwen3.6 35B · 3B active at 4-bit, the M1 Pro 32GB runs at 25.4 tokens per second (one run) and the M2 Max 32GB at 39.3 (2 runs). Those are community reports whose engines and settings differ, so the gap is a rough sign, not a controlled measure of the two cards. Memory bandwidth, which caps how fast a card can write, is 2.0x higher on the M2 Max 32GB (205 GB/s on the M1 Pro 32GB, 410 on the M2 Max 32GB).
- Memory
- 32GB unified
- Memory bandwidth
- 205 GB/s
- FP16 compute
- 5.2 TFLOPS
- Reports
- 2
- Memory
- 32GB unified
- Memory bandwidth
- 410 GB/s
- FP16 compute
- 13.6 TFLOPS
- Reports
- 2
Measured on both
Median tokens per second from plain runs (one device, one request, no speculative decoding, the whole model in the device's memory) of the same model size at the same bit class. Each side shows the engines and reported context behind its median. Context can mean a configured window or prompt depth, so these are community comparisons with differing settings. How to read these
| Model | M1 Pro 32GB | M2 Max 32GB |
|---|---|---|
| Qwen3.6 35B · 3B active4-bit | 25.4one runllama.cpp32K context | 39.32 runsllama.cpp, 1 not stated4K to 60K context |
Estimated by the calculator
The quant the calculator recommends for each card and its estimated speed at a 32,768-token context with 32 GB of system RAM, from memory bandwidth and the model's shape. Where a model was also measured above, the measurement wins.
| Model | M1 Pro 32GB | M2 Max 32GB |
|---|---|---|
| Qwen3.6 35B · 3B active | 40.7 t/sQ3_K_M | 76.1 t/sQ3_K_M |
| Qwen3.8 27B | 11.2 t/sQ4_K_S | 20.9 t/sQ4_K_S |
| Qwen3.8 125B · 6B active | doesn't fit at these settings | doesn't fit at these settings |
| DeepSeek V4 Flash 284B · 13B active | doesn't fit at these settings | doesn't fit at these settings |
| Qwen3.6 27B | 11.2 t/sQ4_K_S | 20.9 t/sQ4_K_S |
| GLM-5.3 320B · 18B active | doesn't fit at these settings | doesn't fit at these settings |
| Gemma 4 26B · 4B active | 24.6 t/sQ4_K_M | 46.1 t/sQ4_K_M |
Change the context, RAM or model in the calculator: M1 Pro 32GB · M2 Max 32GB
Every report on each card, with its source: M1 Pro 32GB · M2 Max 32GB