M5 Max 36GB vs M5 Pro 48GB for local LLMs
14 reports on the M5 Max 36GB and 9 on the M5 Pro 48GB
Which is faster for local LLMs?
Nobody has reported the same model at the same quant on both cards yet, so there's no measured head-to-head. Memory bandwidth, which caps how fast a card can write, is 1.5x higher on the M5 Max 36GB (461 GB/s on the M5 Max 36GB, 307 on the M5 Pro 48GB). The estimates below compare them on the models people run most.
M5 Max 36GB
- Memory
- 36GB unified
- Memory bandwidth
- 461 GB/s
- FP16 compute
- not on record
- Reports
- 14
M5 Pro 48GB
- Memory
- 48GB unified
- Memory bandwidth
- 307 GB/s
- FP16 compute
- not on record
- Reports
- 9
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.
| Model | M5 Max 36GB | M5 Pro 48GB |
|---|---|---|
| Qwen3.8 27B | 19.7 t/sQ5_K_M | 12.0 t/sQ6_K |
| Qwen3.8 125B · 6B active | doesn't fit at these settings | doesn't fit at these settings |
| Qwen3.6 35B · 3B active | 75.9 t/sQ4_K_M | 47.5 t/sQ5_K_M |
| DeepSeek V4 Flash 284B · 13B active | doesn't fit at these settings | doesn't fit at these settings |
| Qwen3.6 27B | 19.7 t/sQ5_K_M | 12.0 t/sQ6_K |
| Gemma 4 26B · 4B active | 50.2 t/sQ5_K_M | 23.2 t/sQ8_0 |
Change the context, RAM or model in the calculator: M5 Max 36GB · M5 Pro 48GB
Every report on each card, with its source: M5 Max 36GB · M5 Pro 48GB