AMD RX 7900 XT vs AMD Strix Halo 128GB for local LLMs
10 reports on the AMD RX 7900 XT and 313 on the AMD Strix Halo 128GB
Which is faster for local LLMs?
Nobody has reported the same model at the same quant on both cards yet, so there's no measured head-to-head. Memory bandwidth, which caps how fast a card can write, is 3.1x higher on the AMD RX 7900 XT (800 GB/s on the AMD RX 7900 XT, 256 on the AMD Strix Halo 128GB). The estimates below compare them on the models people run most.
AMD RX 7900 XT
- Memory
- 20GB
- Memory bandwidth
- 800 GB/s
- FP16 compute
- 103 TFLOPS
- Reports
- 10
AMD Strix Halo 128GB
- Memory
- 128GB unified
- Memory bandwidth
- 256 GB/s
- FP16 compute
- 59 TFLOPS
- Reports
- 313
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.
| Model | AMD RX 7900 XT | AMD Strix Halo 128GB |
|---|---|---|
| Qwen3.8 27B | 37.2 t/sQ3_K_M | 3.5 t/sFP16 |
| Qwen3.8 125B · 6B active | 19.2 t/sQ2_K, experts in RAM | 12.6 t/sQ6_K |
| Qwen3.6 35B · 3B active | 147.9 t/sQ3_K_S | 12.6 t/sFP16 |
| DeepSeek V4 Flash 284B · 13B active | doesn't fit at these settings | 33.5 t/sQ2_K |
| Qwen3.6 27B | 37.2 t/sQ3_K_M | 3.5 t/sFP16 |
| Gemma 4 26B · 4B active | 83.9 t/sQ4_K_S | 9.5 t/sFP16 |
Change the context, RAM or model in the calculator: AMD RX 7900 XT · AMD Strix Halo 128GB
Every report on each card, with its source: AMD RX 7900 XT · AMD Strix Halo 128GB