M5 Max 128GB vs AMD Strix Halo 128GB for local LLMs
32 reports on the M5 Max 128GB and 110 on the AMD Strix Halo 128GB
Which is faster for local LLMs?
On Qwen3.8 125B · 6B active at 4-bit, the M5 Max 128GB runs at 55.0 tokens per second (one run) and the AMD Strix Halo 128GB at 22.0 (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 2.4x higher on the M5 Max 128GB (614 GB/s on the M5 Max 128GB, 256 on the AMD Strix Halo 128GB). Across the 3 models both have been measured on, the M5 Max 128GB's median is higher on 3 and the AMD Strix Halo 128GB's on 0.
- Memory
- 128GB unified
- Memory bandwidth
- 614 GB/s
- FP16 compute
- not on record
- Reports
- 32
- 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 | M5 Max 128GB | AMD Strix Halo 128GB |
|---|---|---|
| Qwen3.8 125B · 6B active4-bit | 55.0one runengine not statedcontext not stated | 22.04 runsGufo, llama.cpp128K to 160K context |
| Qwen3.6 35B · 3B active8-bit | 79.4one runllama.cpp125K context | 50.03 runsGufo, llama.cpp, 1 not stated512K context, 2 not stated |
| Nex-N2.5-mini 35B · 3B active4-bit | 133.6one runMLXcontext not stated | 76.9one runengine not statedcontext 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 | M5 Max 128GB | AMD Strix Halo 128GB |
|---|---|---|
| Qwen3.8 125B · 6B active | 41.2 t/sQ5_K_S | 12.6 t/sQ6_K |
| Qwen3.6 35B · 3B active | 28.5 t/sFP16 | 12.6 t/sFP16 |
| Nex-N2.5-mini 35B · 3B active | 28.5 t/sFP16 | 12.6 t/sFP16 |
| Qwen3.8 27B | 9.0 t/sFP16 | 3.5 t/sFP16 |
| DeepSeek V4 Flash 284B · 13B active | 64.8 t/sQ2_K | 33.5 t/sQ2_K |
| Qwen3.6 27B | 9.0 t/sFP16 | 3.5 t/sFP16 |
| GLM-5.3 320B · 18B active | doesn't fit at these settings | 11.1 t/sQ2_K |
| Gemma 4 26B · 4B active | 24.4 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: M5 Max 128GB · AMD Strix Halo 128GB
Every report on each card, with its source: M5 Max 128GB · AMD Strix Halo 128GB