llamaperf

AMD Gorgon Halo 192GB vs NVIDIA RTX 5090 for local LLMs

8 reports on the AMD Gorgon Halo 192GB and 197 on the NVIDIA RTX 5090

Which is faster for local LLMs?

On Qwen3.8 27B at 6-bit, the AMD Gorgon Halo 192GB has 9.0 generation tokens/s (one run); prompt processing 463.0 tokens/s (one run); the NVIDIA RTX 5090 has 69.1 generation tokens/s (2 runs); prompt processing 479.2 tokens/s (one run). 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 6.6x higher on the NVIDIA RTX 5090 (273 GB/s on the AMD Gorgon Halo 192GB, 1,792 on the NVIDIA RTX 5090).

AMD Gorgon Halo 192GB
Memory
192GB unified
Memory bandwidth
273 GB/s
FP16 compute
61.4 TFLOPS
Reports
8
NVIDIA RTX 5090
Memory
32GB
Memory bandwidth
1,792 GB/s
FP16 compute
419 TFLOPS
Reports
197

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 192GBNVIDIA RTX 5090
Qwen3.8 27B6-bit9.0one runPP 463.0 (one run)llama.cppcontext not stated69.12 runsPP 479.2 (one run)llama.cpp, 1 not stated32K to 160K context

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 192GBNVIDIA RTX 5090
Qwen3.8 27B2.8 t/sFP1644.9 t/sQ6_K
Qwen3.8 125B · 6B active9.5 t/sQ8_020.3 t/sQ2_K, experts in RAM
Qwen3.6 35B · 3B active10.0 t/sFP16163.0 t/sQ5_K_M
DeepSeek V4 Flash 284B · 13B active12.5 t/sQ4_K_Mdoesn't fit at these settings
DeepSeek V4.1 Flash 552B · 16B active16.7 t/sQ2_Kdoesn't fit at these settings
Qwen3.6 27B2.8 t/sFP1644.9 t/sQ6_K
Gemma 4 26B · 4B active7.5 t/sFP16114.5 t/sQ6_K

Change the context, RAM or model in the calculator: AMD Gorgon Halo 192GB · NVIDIA RTX 5090

Every report on each card, with its source: AMD Gorgon Halo 192GB · NVIDIA RTX 5090

More comparisons