llamaperf

M5 Ultra 96GB vs AMD Strix Halo 128GB for local LLMs

12 reports on the M5 Ultra 96GB and 348 on the AMD Strix Halo 128GB

Which is faster for local LLMs?

On Qwen3.8 27B at 8-bit, the M5 Ultra 96GB has 15.0 generation tokens/s (one run); the AMD Strix Halo 128GB has 7.5 generation tokens/s (3 runs); prompt processing 257.8 tokens/s (2 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 4.8x higher on the M5 Ultra 96GB (1,229 GB/s on the M5 Ultra 96GB, 256 on the AMD Strix Halo 128GB).

M5 Ultra 96GB
Memory
96GB unified
Memory bandwidth
1,229 GB/s
FP16 compute
not on record
Reports
12
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

ModelM5 Ultra 96GBAMD Strix Halo 128GB
Qwen3.8 27B8-bit15.0one runengine not statedcontext not stated7.53 runsPP 257.8 (2 runs)llama.cpp, 1 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.

ModelM5 Ultra 96GBAMD Strix Halo 128GB
Qwen3.8 27B14.9 t/sFP163.5 t/sFP16
Qwen3.8 125B · 6B active103.1 t/sQ3_K_M12.6 t/sQ6_K
Qwen3.6 35B · 3B active107.0 t/sQ8_012.6 t/sFP16
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 27B14.9 t/sFP163.5 t/sFP16
Gemma 4 26B · 4B active35.5 t/sFP169.5 t/sFP16

Change the context, RAM or model in the calculator: M5 Ultra 96GB · AMD Strix Halo 128GB

Every report on each card, with its source: M5 Ultra 96GB · AMD Strix Halo 128GB

More comparisons