M1 8GB vs AMD Strix Halo 128GB for local LLMs
2 reports on the M1 8GB and 110 on the AMD Strix Halo 128GB
Which is faster for local LLMs?
On LFM2.5 2.6B at 4-bit, the M1 8GB runs at 22.0 tokens per second (one run) and the AMD Strix Halo 128GB at 113.0 (one run). 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 3.7x higher on the AMD Strix Halo 128GB (68 GB/s on the M1 8GB, 256 on the AMD Strix Halo 128GB).
- Memory
- 8GB unified
- Memory bandwidth
- 68 GB/s
- FP16 compute
- 2.6 TFLOPS
- Reports
- 2
- Memory
- 128GB unified
- Memory bandwidth
- 256 GB/s
- FP16 compute
- 59 TFLOPS
- Reports
- 110
Measured on both
Median tokens per second 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 8GB | AMD Strix Halo 128GB |
|---|---|---|
| LFM2.5 2.6B4-bit | 22.0one runllama.cpp32K context | 113.0one runllama.cpp125K context |
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 8GB | AMD Strix Halo 128GB |
|---|---|---|
| LFM2.5 2.6B | 46.9 t/sQ3_K_M | 36.5 t/sFP16 |
| Qwen3.8 27B | doesn't fit at these settings | 3.5 t/sFP16 |
| Qwen3.8 125B · 6B active | doesn't fit at these settings | 12.6 t/sQ6_K |
| DeepSeek V4 Flash 284B · 13B active | doesn't fit at these settings | 33.5 t/sQ2_K |
| Qwen3.6 35B · 3B active | doesn't fit at these settings | 12.6 t/sFP16 |
| Qwen3.6 27B | doesn't fit at these settings | 3.5 t/sFP16 |
| GLM-5.3 320B · 18B active | doesn't fit at these settings | 11.1 t/sQ2_K |
Change the context, RAM or model in the calculator: M1 8GB · AMD Strix Halo 128GB
Every report on each card, with its source: M1 8GB · AMD Strix Halo 128GB