M4 Max 128GB vs AMD Strix Halo 128GB for local LLMs
52 reports on the M4 Max 128GB and 313 on the AMD Strix Halo 128GB
Which is faster for local LLMs?
On Qwen3.8 125B · 6B active at 4-bit, the M4 Max 128GB has 57.2 generation tokens/s (2 runs); prompt processing 586.0 tokens/s (one run); the AMD Strix Halo 128GB has 24.5 generation tokens/s (6 runs); prompt processing 1700.5 tokens/s (5 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 2.1x higher on the M4 Max 128GB (546 GB/s on the M4 Max 128GB, 256 on the AMD Strix Halo 128GB). Across 10 shared models with generation measurements on both cards, the M4 Max 128GB's median is higher on 9 and the AMD Strix Halo 128GB's on 1.
- Memory
- 128GB unified
- Memory bandwidth
- 546 GB/s
- FP16 compute
- 18.4 TFLOPS
- Reports
- 52
- Memory
- 128GB unified
- Memory bandwidth
- 256 GB/s
- FP16 compute
- 59 TFLOPS
- Reports
- 313
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 | M4 Max 128GB | AMD Strix Halo 128GB |
|---|---|---|
| Qwen3.8 125B · 6B active4-bit | 57.22 runsPP 586.0 (one run)oMLX, 1 not statedcontext not stated | 24.56 runsPP 1700.5 (5 runs)Gufo, llama.cpp, 1 not stated128K to 160K context, 3 not stated |
| Qwen3.6 35B · 3B active4-bit | 81.1one runPP 1423.5 (one run)llama.cppcontext not stated | 60.07 runsPP 1005.3 (7 runs)llama.cpp, 3 not stated30K context, 6 not stated |
| gpt-oss 21B · 3.6B active4-bit | 123.1one runPP 1577.0 (one run)llama.cppcontext not stated | 71.74 runsPP 1088.6 (4 runs)llama.cpp, 3 not statedcontext not stated |
| gpt-oss 117B · 5.1B active4-bit | 85.4one runPP 809.5 (one run)llama.cppcontext not stated | 52.64 runsPP 572.5 (4 runs)llama.cpp, 2 not statedcontext not stated |
| Qwen3.8 27B4-bit | 21.8one runPP 236.6 (one run)llama.cppcontext not stated | 13.14 runsPP 378.2 (3 runs)llama.cpp, 1 not stated32K context, 3 not stated |
| Qwen3 30B · 3B active4-bit | 127.7one runvllm-mlxcontext not stated | 73.73 runsPP 920.0 (3 runs)llama.cpp48K context, 2 not stated |
| Qwen3.8 27B8-bit | 15.7one runPP 255.7 (one run)llama.cppcontext not stated | 7.53 runsPP 257.8 (2 runs)llama.cpp, 1 not statedcontext not stated |
| Gemma 4 26B · 4B active4-bit | 88.1one runPP 1408.1 (one run)llama.cppcontext not stated | 67.32 runsPP 4061.0 (2 runs)Gufocontext not stated |
| Qwen3.5 122B · 10B active4-bit | 15.6one runllama.cppcontext not stated | 22.4one runPP 287.0 (one run)engine not statedcontext not stated |
| Qwen3.5 9B4-bit | 68.0one runPP 832.1 (one run)llama.cppcontext not stated | 31.1one runPP 819.2 (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 | M4 Max 128GB | AMD Strix Halo 128GB |
|---|---|---|
| Qwen3.8 125B · 6B active | 30.7 t/sQ5_K_S | 12.6 t/sQ6_K |
| Qwen3.6 35B · 3B active | 21.2 t/sFP16 | 12.6 t/sFP16 |
| gpt-oss 21B · 3.6B active | 40.5 t/sFP16 | 21.1 t/sFP16 |
| gpt-oss 117B · 5.1B active | 38.6 t/sQ5_K_S | 15.8 t/sQ6_K |
| Qwen3.8 27B | 6.7 t/sFP16 | 3.5 t/sFP16 |
| Qwen3 30B · 3B active | 23.7 t/sFP16 | 12.6 t/sFP16 |
| Gemma 4 26B · 4B active | 18.2 t/sFP16 | 9.5 t/sFP16 |
| Qwen3.5 122B · 10B active | 18.9 t/sQ5_K_S | 7.7 t/sQ6_K |
| Qwen3.5 9B | 20.2 t/sFP16 | 10.5 t/sFP16 |
| DeepSeek V4 Flash 284B · 13B active | 48.3 t/sQ2_K | 33.5 t/sQ2_K |
| Qwen3.6 27B | 6.7 t/sFP16 | 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 |
| Gemma 4 31B | 5.9 t/sFP16 | 3.1 t/sFP16 |
| Qwen3.5 35B · 3B active | 21.2 t/sFP16 | 12.6 t/sFP16 |
Change the context, RAM or model in the calculator: M4 Max 128GB · AMD Strix Halo 128GB
Every report on each card, with its source: M4 Max 128GB · AMD Strix Halo 128GB