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).
- Memory
- 192GB unified
- Memory bandwidth
- 273 GB/s
- FP16 compute
- 61.4 TFLOPS
- Reports
- 8
- 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
| Model | AMD Gorgon Halo 192GB | NVIDIA RTX 5090 |
|---|---|---|
| Qwen3.8 27B6-bit | 9.0one runPP 463.0 (one run)llama.cppcontext not stated | 69.12 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.
| Model | AMD Gorgon Halo 192GB | NVIDIA RTX 5090 |
|---|---|---|
| Qwen3.8 27B | 2.8 t/sFP16 | 44.9 t/sQ6_K |
| Qwen3.8 125B · 6B active | 9.5 t/sQ8_0 | 20.3 t/sQ2_K, experts in RAM |
| Qwen3.6 35B · 3B active | 10.0 t/sFP16 | 163.0 t/sQ5_K_M |
| DeepSeek V4 Flash 284B · 13B active | 12.5 t/sQ4_K_M | doesn't fit at these settings |
| DeepSeek V4.1 Flash 552B · 16B active | 16.7 t/sQ2_K | doesn't fit at these settings |
| Qwen3.6 27B | 2.8 t/sFP16 | 44.9 t/sQ6_K |
| Gemma 4 26B · 4B active | 7.5 t/sFP16 | 114.5 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