M1 Ultra 128GB vs M2 Max 64GB for local LLMs
11 reports on the M1 Ultra 128GB and 20 on the M2 Max 64GB
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 2.0x higher on the M1 Ultra 128GB (819 GB/s on the M1 Ultra 128GB, 410 on the M2 Max 64GB). The estimates below compare them on the models people run most.
M1 Ultra 128GB
- Memory
- 128GB unified
- Memory bandwidth
- 819 GB/s
- FP16 compute
- 21 TFLOPS
- Reports
- 11
M2 Max 64GB
- Memory
- 64GB unified
- Memory bandwidth
- 410 GB/s
- FP16 compute
- 13.6 TFLOPS
- Reports
- 20
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 128GB | M2 Max 64GB |
|---|---|---|
| Qwen3.8 27B | 7.5 t/sFP16 | 10.4 t/sQ8_0 |
| Qwen3.8 125B · 6B active | 34.0 t/sQ5_K_S | 47.5 t/sQ2_K |
| Qwen3.6 35B · 3B active | 23.5 t/sFP16 | 32.9 t/sQ8_0 |
| DeepSeek V4 Flash 284B · 13B active | 53.5 t/sQ2_K | doesn't fit at these settings |
| Qwen3.6 27B | 7.5 t/sFP16 | 10.4 t/sQ8_0 |
| Gemma 4 26B · 4B active | 20.2 t/sFP16 | 28.2 t/sQ8_0 |
Change the context, RAM or model in the calculator: M1 Ultra 128GB · M2 Max 64GB
Every report on each card, with its source: M1 Ultra 128GB · M2 Max 64GB