M1 Ultra 128GB vs M2 Ultra 192GB for local LLMs
11 reports on the M1 Ultra 128GB and 9 on the M2 Ultra 192GB
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 about the same on both (819 GB/s on the M1 Ultra 128GB, 819 on the M2 Ultra 192GB). 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 Ultra 192GB
- Memory
- 192GB unified
- Memory bandwidth
- 819 GB/s
- FP16 compute
- 27.2 TFLOPS
- 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 | M1 Ultra 128GB | M2 Ultra 192GB |
|---|---|---|
| Qwen3.8 27B | 7.5 t/sFP16 | 8.3 t/sFP16 |
| Qwen3.8 125B · 6B active | 34.0 t/sQ5_K_S | 33.0 t/sQ6_K |
| Qwen3.6 35B · 3B active | 23.5 t/sFP16 | 29.9 t/sFP16 |
| DeepSeek V4 Flash 284B · 13B active | 53.5 t/sQ2_K | 62.8 t/sQ3_K_S |
| Qwen3.6 27B | 7.5 t/sFP16 | 8.3 t/sFP16 |
| Gemma 4 26B · 4B active | 20.2 t/sFP16 | 22.5 t/sFP16 |
Change the context, RAM or model in the calculator: M1 Ultra 128GB · M2 Ultra 192GB
Every report on each card, with its source: M1 Ultra 128GB · M2 Ultra 192GB