M5 Max 48GB vs AMD Strix Halo 128GB for local LLMs
67 reports on the M5 Max 48GB and 320 on the AMD Strix Halo 128GB
Which is faster for local LLMs?
On Qwen3.6 35B · 3B active at 4-bit, the M5 Max 48GB has 137.7 generation tokens/s (2 runs); prompt processing 3338.1 tokens/s (2 runs); the AMD Strix Halo 128GB has 60.0 generation tokens/s (7 runs); prompt processing 1005.3 tokens/s (7 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 48GB (614 GB/s on the M5 Max 48GB, 256 on the AMD Strix Halo 128GB). Across 9 shared models with generation measurements on both cards, the M5 Max 48GB's median is higher on 9 and the AMD Strix Halo 128GB's on 0.
- Memory
- 48GB unified
- Memory bandwidth
- 614 GB/s
- FP16 compute
- not on record
- Reports
- 67
- Memory
- 128GB unified
- Memory bandwidth
- 256 GB/s
- FP16 compute
- 59 TFLOPS
- Reports
- 320
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 | M5 Max 48GB | AMD Strix Halo 128GB |
|---|---|---|
| Qwen3.6 35B · 3B active4-bit | 137.72 runsPP 3338.1 (2 runs)llama.cpp, MLXcontext not stated | 60.07 runsPP 1005.3 (7 runs)llama.cpp, 3 not stated30K context, 6 not stated |
| Qwen3 30B · 3B active4-bit | 148.5one runPP 3496.9 (one run)llama.cppcontext not stated | 73.73 runsPP 920.0 (3 runs)llama.cpp48K context, 2 not stated |
| Gemma 4 31B4-bit | 25.2one runPP 626.5 (one run)llama.cppcontext not stated | 11.52 runsPP 559.3 (2 runs)Gufocontext not stated |
| Gemma 4 26B · 4B active4-bit | 116.9one runPP 3423.2 (one run)llama.cppcontext not stated | 67.32 runsPP 4061.0 (2 runs)Gufocontext not stated |
| Llama 3.2 3B4-bit | 199.9one runPP 6122.5 (one run)llama.cppcontext not stated | 89.12 runsPP 1915.0 (2 runs)llama.cpp, 1 not statedcontext not stated |
| Qwen3.5 35B · 3B active4-bit | 111.2one runPP 3378.3 (one run)llama.cppcontext not stated | 52.42 runsPP 1017.0 (one run)llama.cpp, 1 not stated128K context, 1 not stated |
| Gemma 3 27B4-bit | 29.9one runPP 751.0 (one run)llama.cppcontext not stated | 13.0one runPP 382.5 (one run)llama.cppcontext not stated |
| Qwen3.5 9B4-bit | 86.5one runPP 2369.3 (one run)llama.cppcontext not stated | 31.1one runPP 819.2 (one run)engine not statedcontext not stated |
| Qwen3.5 27B4-bit | 29.2one runPP 730.5 (one run)llama.cppcontext not stated | 12.1one runPP 310.0 (one run)engine 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 48GB | AMD Strix Halo 128GB |
|---|---|---|
| Qwen3.6 35B · 3B active | 88.4 t/sQ5_K_M | 12.6 t/sFP16 |
| Qwen3 30B · 3B active | 104.1 t/sQ5_K_S | 12.6 t/sFP16 |
| Gemma 4 31B | 19.4 t/sQ6_K | 3.1 t/sFP16 |
| Gemma 4 26B · 4B active | 43.2 t/sQ8_0 | 9.5 t/sFP16 |
| Llama 3.2 3B | 81.4 t/sFP16 | 31.6 t/sFP16 |
| Qwen3.5 35B · 3B active | 88.4 t/sQ5_K_M | 12.6 t/sFP16 |
| Gemma 3 27B | 22.3 t/sQ6_K | 3.5 t/sFP16 |
| Qwen3.5 9B | 27.1 t/sFP16 | 10.5 t/sFP16 |
| Qwen3.5 27B | 22.3 t/sQ6_K | 3.5 t/sFP16 |
| Qwen3.8 27B | 22.3 t/sQ6_K | 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 27B | 22.3 t/sQ6_K | 3.5 t/sFP16 |
| DeepSeek V4.1 Flash 552B · 16B active | doesn't fit at these settings | doesn't fit at these settings |
| 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: M5 Max 48GB · AMD Strix Halo 128GB
Every report on each card, with its source: M5 Max 48GB · AMD Strix Halo 128GB