llamaperf

AMD Gorgon Halo 192GB vs AMD Strix Halo 128GB for local LLMs

8 reports on the AMD Gorgon Halo 192GB and 348 on the AMD Strix Halo 128GB

Which is faster for local LLMs?

On gpt-oss 117B · 5.1B active at 4-bit, the AMD Gorgon Halo 192GB has 49.0 generation tokens/s (2 runs); prompt processing 760.0 tokens/s (2 runs); the AMD Strix Halo 128GB has 52.6 generation tokens/s (4 runs); prompt processing 572.5 tokens/s (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 7% higher on the AMD Gorgon Halo 192GB (273 GB/s on the AMD Gorgon Halo 192GB, 256 on the AMD Strix Halo 128GB). Across 2 shared models with generation measurements on both cards, the AMD Gorgon Halo 192GB's median is higher on 1 and the AMD Strix Halo 128GB's on 1.

AMD Gorgon Halo 192GB
Memory
192GB unified
Memory bandwidth
273 GB/s
FP16 compute
61.4 TFLOPS
Reports
8
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

ModelAMD Gorgon Halo 192GBAMD Strix Halo 128GB
gpt-oss 117B · 5.1B active4-bit49.02 runsPP 760.0 (2 runs)llama.cpp512 context, 1 not stated52.64 runsPP 572.5 (4 runs)llama.cpp, 2 not statedcontext not stated
Qwen3.8 27B8-bit8.1one runPP 466.0 (one run)llama.cppcontext 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.

ModelAMD Gorgon Halo 192GBAMD Strix Halo 128GB
gpt-oss 117B · 5.1B active11.7 t/sQ8_015.8 t/sQ6_K
Qwen3.8 27B2.8 t/sFP163.5 t/sFP16
Qwen3.8 125B · 6B active9.5 t/sQ8_012.6 t/sQ6_K
Qwen3.6 35B · 3B active10.0 t/sFP1612.6 t/sFP16
DeepSeek V4 Flash 284B · 13B active12.5 t/sQ4_K_M33.5 t/sQ2_K
DeepSeek V4.1 Flash 552B · 16B active16.7 t/sQ2_Kdoesn't fit at these settings
Qwen3.6 27B2.8 t/sFP163.5 t/sFP16
Gemma 4 26B · 4B active7.5 t/sFP169.5 t/sFP16

Change the context, RAM or model in the calculator: AMD Gorgon Halo 192GB · AMD Strix Halo 128GB

Every report on each card, with its source: AMD Gorgon Halo 192GB · AMD Strix Halo 128GB

More comparisons