M1 Ultra 128GB vs AMD Strix Halo 128GB for local LLMs
11 reports on the M1 Ultra 128GB and 318 on the AMD Strix Halo 128GB
Which is faster for local LLMs?
On gpt-oss 117B · 5.1B active at 4-bit, the M1 Ultra 128GB has 65.5 generation tokens/s (one run); prompt processing 392.4 tokens/s (one run); the AMD Strix Halo 128GB has 52.6 generation tokens/s (4 runs); prompt processing 572.5 tokens/s (4 runs). Those are community reports whose engines and settings differ, so the gap is a rough sign, not a controlled measure of the two cards. Memory bandwidth, which caps how fast a card can write, is 3.2x higher on the M1 Ultra 128GB (819 GB/s on the M1 Ultra 128GB, 256 on the AMD Strix Halo 128GB). Across 2 shared models with generation measurements on both cards, the M1 Ultra 128GB's median is higher on 2 and the AMD Strix Halo 128GB's on 0.
- Memory
- 128GB unified
- Memory bandwidth
- 819 GB/s
- FP16 compute
- 21 TFLOPS
- Reports
- 11
- Memory
- 128GB unified
- Memory bandwidth
- 256 GB/s
- FP16 compute
- 59 TFLOPS
- Reports
- 318
Measured on both
Generation and prompt processing speeds from plain runs (one device, one request, no speculative decoding, the whole model in the device's memory) of the same model size at the same bit class. Each side shows the engines and reported context behind its median. Context can mean a configured window or prompt depth, so these are community comparisons with differing settings. How to read these
| Model | M1 Ultra 128GB | AMD Strix Halo 128GB |
|---|---|---|
| gpt-oss 117B · 5.1B active4-bit | 65.5one runPP 392.4 (one run)engine not statedcontext not stated | 52.64 runsPP 572.5 (4 runs)llama.cpp, 2 not statedcontext not stated |
| Qwen3.8 27B4-bit | 25.1one runPP 153.3 (one run)engine not statedcontext not stated | 13.14 runsPP 378.2 (3 runs)llama.cpp, 1 not stated32K context, 3 not stated |
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. Where a model was also measured above, the measurement wins.
| Model | M1 Ultra 128GB | AMD Strix Halo 128GB |
|---|---|---|
| gpt-oss 117B · 5.1B active | 42.7 t/sQ5_K_S | 15.8 t/sQ6_K |
| Qwen3.8 27B | 7.5 t/sFP16 | 3.5 t/sFP16 |
| Qwen3.8 125B · 6B active | 34.0 t/sQ5_K_S | 12.6 t/sQ6_K |
| Qwen3.6 35B · 3B active | 23.5 t/sFP16 | 12.6 t/sFP16 |
| DeepSeek V4 Flash 284B · 13B active | 53.5 t/sQ2_K | 33.5 t/sQ2_K |
| Qwen3.6 27B | 7.5 t/sFP16 | 3.5 t/sFP16 |
| Gemma 4 26B · 4B active | 20.2 t/sFP16 | 9.5 t/sFP16 |
| DeepSeek V4.1 Flash 552B · 16B active | doesn't fit at these settings | doesn't fit at these settings |
Change the context, RAM or model in the calculator: M1 Ultra 128GB · AMD Strix Halo 128GB
Every report on each card, with its source: M1 Ultra 128GB · AMD Strix Halo 128GB