M2 Ultra 64GB vs AMD Strix Halo 128GB for local LLMs
1 report on the M2 Ultra 64GB and 320 on the AMD Strix Halo 128GB
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 3.2x higher on the M2 Ultra 64GB (819 GB/s on the M2 Ultra 64GB, 256 on the AMD Strix Halo 128GB). The estimates below compare them on the models people run most.
M2 Ultra 64GB
- Memory
- 64GB unified
- Memory bandwidth
- 819 GB/s
- FP16 compute
- 27.2 TFLOPS
- Reports
- 1
AMD Strix Halo 128GB
- Memory
- 128GB unified
- Memory bandwidth
- 256 GB/s
- FP16 compute
- 59 TFLOPS
- Reports
- 320
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 | M2 Ultra 64GB | AMD Strix Halo 128GB |
|---|---|---|
| Qwen3.8 27B | 16.6 t/sQ8_0 | 3.5 t/sFP16 |
| Qwen3.8 125B · 6B active | 75.7 t/sQ2_K | 12.6 t/sQ6_K |
| Qwen3.6 35B · 3B active | 52.4 t/sQ8_0 | 12.6 t/sFP16 |
| DeepSeek V4 Flash 284B · 13B active | doesn't fit at these settings | 33.5 t/sQ2_K |
| Qwen3.6 27B | 16.6 t/sQ8_0 | 3.5 t/sFP16 |
| Gemma 4 26B · 4B active | 44.9 t/sQ8_0 | 9.5 t/sFP16 |
Change the context, RAM or model in the calculator: M2 Ultra 64GB · AMD Strix Halo 128GB
Every report on each card, with its source: M2 Ultra 64GB · AMD Strix Halo 128GB