M1 Max 32GB vs M5 Max 36GB for local LLMs
2 reports on the M1 Max 32GB and 14 on the M5 Max 36GB
Which is faster for local LLMs?
On Qwen3.8 27B at 4-bit, the M1 Max 32GB has 15.8 generation tokens/s (one run); prompt processing 81.8 tokens/s (one run); the M5 Max 36GB has 22.4 generation tokens/s (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 13% higher on the M5 Max 36GB (410 GB/s on the M1 Max 32GB, 461 on the M5 Max 36GB).
- Memory
- 32GB unified
- Memory bandwidth
- 410 GB/s
- FP16 compute
- 10.4 TFLOPS
- Reports
- 2
- Memory
- 36GB unified
- Memory bandwidth
- 461 GB/s
- FP16 compute
- not on record
- Reports
- 14
Measured on both
Generation and prompt processing speeds 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 Max 32GB | M5 Max 36GB |
|---|---|---|
| Qwen3.8 27B4-bit | 15.8one runPP 81.8 (one run)MLXcontext not stated | 22.42 runsOllama, 1 not stated16K context, 1 not stated |
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 Max 32GB | M5 Max 36GB |
|---|---|---|
| Qwen3.8 27B | 20.1 t/sQ4_K_S | 19.7 t/sQ5_K_M |
| Qwen3.8 125B · 6B active | doesn't fit at these settings | doesn't fit at these settings |
| Qwen3.6 35B · 3B active | 73.2 t/sQ3_K_M | 75.9 t/sQ4_K_M |
| DeepSeek V4 Flash 284B · 13B active | doesn't fit at these settings | doesn't fit at these settings |
| Qwen3.6 27B | 20.1 t/sQ4_K_S | 19.7 t/sQ5_K_M |
| Gemma 4 26B · 4B active | 44.3 t/sQ4_K_M | 50.2 t/sQ5_K_M |
| DeepSeek V4.1 Flash 552B · 16B active | doesn't fit at these settings | doesn't fit at these settings |
Change the context, RAM or model in the calculator: M1 Max 32GB · M5 Max 36GB
Every report on each card, with its source: M1 Max 32GB · M5 Max 36GB