M1 Ultra 64GB vs M5 Max 48GB for local LLMs
4 reports on the M1 Ultra 64GB and 67 on the M5 Max 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 33% higher on the M1 Ultra 64GB (819 GB/s on the M1 Ultra 64GB, 614 on the M5 Max 48GB). The estimates below compare them on the models people run most.
M1 Ultra 64GB
- Memory
- 64GB unified
- Memory bandwidth
- 819 GB/s
- FP16 compute
- 21 TFLOPS
- Reports
- 4
M5 Max 48GB
- Memory
- 48GB unified
- Memory bandwidth
- 614 GB/s
- FP16 compute
- not on record
- Reports
- 67
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 | M1 Ultra 64GB | M5 Max 48GB |
|---|---|---|
| Qwen3.8 27B | 14.9 t/sQ8_0 | 22.3 t/sQ6_K |
| Qwen3.8 125B · 6B active | 68.0 t/sQ2_K | doesn't fit at these settings |
| Qwen3.6 35B · 3B active | 47.1 t/sQ8_0 | 88.4 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 | 14.9 t/sQ8_0 | 22.3 t/sQ6_K |
| Gemma 4 26B · 4B active | 40.4 t/sQ8_0 | 43.2 t/sQ8_0 |
Change the context, RAM or model in the calculator: M1 Ultra 64GB · M5 Max 48GB
Every report on each card, with its source: M1 Ultra 64GB · M5 Max 48GB