llamaperf

M6 32GB vs AMD Strix Halo 128GB for local LLMs

22 reports on the M6 32GB and 348 on the AMD Strix Halo 128GB

Which is faster for local LLMs?

On Qwen3.6 35B · 3B active at 4-bit, the M6 32GB has 63.8 generation tokens/s (one run); 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 50% higher on the AMD Strix Halo 128GB (171 GB/s on the M6 32GB, 256 on the AMD Strix Halo 128GB). Across 3 shared models with generation measurements on both cards, the M6 32GB's median is higher on 1 and the AMD Strix Halo 128GB's on 2.

M6 32GB
Memory
32GB unified
Memory bandwidth
171 GB/s
FP16 compute
not on record
Reports
22
AMD Strix Halo 128GB
Memory
128GB unified
Memory bandwidth
256 GB/s
FP16 compute
59 TFLOPS
Reports
348

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

ModelM6 32GBAMD Strix Halo 128GB
Qwen3.6 35B · 3B active4-bit63.8one runLM Studio32K context60.07 runsPP 1005.3 (7 runs)llama.cpp, 3 not stated30K context, 6 not stated
Gemma 4 26B · 4B active4-bit52.2one runengine not statedcontext not stated67.32 runsPP 4061.0 (2 runs)Gufocontext not stated
Gemma 3 27B4-bit8.9one runPP 11.2 (one run)engine not statedcontext not stated13.0one runPP 382.5 (one run)llama.cppcontext 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.

ModelM6 32GBAMD Strix Halo 128GB
Qwen3.6 35B · 3B active38.2 t/sQ3_K_M12.6 t/sFP16
Gemma 4 26B · 4B active23.2 t/sQ4_K_M9.5 t/sFP16
Gemma 3 27B12.0 t/sQ3_K_M3.5 t/sFP16
Qwen3.8 27B10.5 t/sQ4_K_S3.5 t/sFP16
Qwen3.8 125B · 6B activedoesn't fit at these settings12.6 t/sQ6_K
DeepSeek V4 Flash 284B · 13B activedoesn't fit at these settings33.5 t/sQ2_K
DeepSeek V4.1 Flash 552B · 16B activedoesn't fit at these settingsdoesn't fit at these settings
Qwen3.6 27B10.5 t/sQ4_K_S3.5 t/sFP16
GLM-5.3 320B · 18B activedoesn't fit at these settings11.1 t/sQ2_K

Change the context, RAM or model in the calculator: M6 32GB · AMD Strix Halo 128GB

Every report on each card, with its source: M6 32GB · AMD Strix Halo 128GB

More comparisons