AMD RX 7900 XTX vs AMD Strix Halo 128GB for local LLMs
47 reports on the AMD RX 7900 XTX and 320 on the AMD Strix Halo 128GB
Which is faster for local LLMs?
On Qwen3.8 27B at 4-bit, the AMD RX 7900 XTX has 42.5 generation tokens/s (6 runs); prompt processing 640.0 tokens/s (4 runs); the AMD Strix Halo 128GB has 13.1 generation tokens/s (4 runs); prompt processing 378.2 tokens/s (3 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 3.8x higher on the AMD RX 7900 XTX (960 GB/s on the AMD RX 7900 XTX, 256 on the AMD Strix Halo 128GB). Across 4 shared models with generation measurements on both cards, the AMD RX 7900 XTX's median is higher on 4 and the AMD Strix Halo 128GB's on 0.
- Memory
- 24GB
- Memory bandwidth
- 960 GB/s
- FP16 compute
- 123 TFLOPS
- Reports
- 47
- Memory
- 128GB unified
- Memory bandwidth
- 256 GB/s
- FP16 compute
- 59 TFLOPS
- Reports
- 320
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 RX 7900 XTX | AMD Strix Halo 128GB |
|---|---|---|
| Qwen3.8 27B4-bit | 42.56 runsPP 640.0 (4 runs)llama.cpp, Ollama, 2 not stated64K to 220K context, 3 not stated | 13.14 runsPP 378.2 (3 runs)llama.cpp, 1 not stated32K context, 3 not stated |
| Qwen3.6 35B · 3B active4-bit | 125.5one runPP 1874.7 (one run)llama.cppcontext not stated | 60.07 runsPP 1005.3 (7 runs)llama.cpp, 3 not stated30K context, 6 not stated |
| Gemma 4 31B4-bit | 30.1one runPP 422.3 (one run)llama.cpp32K context | 11.52 runsPP 559.3 (2 runs)Gufocontext not stated |
| Gemma 4 26B · 4B active4-bit | 142.8one runPP 4331.2 (one run)llama.cppcontext not stated | 67.32 runsPP 4061.0 (2 runs)Gufocontext 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.
| Model | AMD RX 7900 XTX | AMD Strix Halo 128GB |
|---|---|---|
| Qwen3.8 27B | 34.8 t/sQ4_K_M | 3.5 t/sFP16 |
| Qwen3.6 35B · 3B active | 123.2 t/sQ4_K_S | 12.6 t/sFP16 |
| Gemma 4 31B | 34.1 t/sQ4_K_S | 3.1 t/sFP16 |
| Gemma 4 26B · 4B active | 78.4 t/sQ5_K_S | 9.5 t/sFP16 |
| Qwen3.8 125B · 6B active | 19.5 t/sQ2_K, experts in RAM | 12.6 t/sQ6_K |
| DeepSeek V4 Flash 284B · 13B active | doesn't fit at these settings | 33.5 t/sQ2_K |
| Qwen3.6 27B | 34.8 t/sQ4_K_M | 3.5 t/sFP16 |
| DeepSeek V4.1 Flash 552B · 16B active | doesn't fit at these settings | doesn't fit at these settings |
| GLM-5.3 320B · 18B active | doesn't fit at these settings | 11.1 t/sQ2_K |
| Qwen3.5 9B | 58.7 t/sQ8_0 | 10.5 t/sFP16 |
Change the context, RAM or model in the calculator: AMD RX 7900 XTX · AMD Strix Halo 128GB
Every report on each card, with its source: AMD RX 7900 XTX · AMD Strix Halo 128GB