NVIDIA RTX 5070 Ti vs AMD Strix Halo 128GB for local LLMs
50 reports on the NVIDIA RTX 5070 Ti and 313 on the AMD Strix Halo 128GB
Which is faster for local LLMs?
On Gemma 4 26B · 4B active at 4-bit, the NVIDIA RTX 5070 Ti has 137.7 generation tokens/s (one run); prompt processing 5951.0 tokens/s (one run); the AMD Strix Halo 128GB has 67.3 generation tokens/s (2 runs); prompt processing 4061.0 tokens/s (2 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 3.5x higher on the NVIDIA RTX 5070 Ti (896 GB/s on the NVIDIA RTX 5070 Ti, 256 on the AMD Strix Halo 128GB).
- Memory
- 16GB
- Memory bandwidth
- 896 GB/s
- FP16 compute
- 176 TFLOPS
- Reports
- 50
- Memory
- 128GB unified
- Memory bandwidth
- 256 GB/s
- FP16 compute
- 59 TFLOPS
- Reports
- 313
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 | NVIDIA RTX 5070 Ti | AMD Strix Halo 128GB |
|---|---|---|
| Gemma 4 26B · 4B active4-bit | 137.7one runPP 5951.0 (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 | NVIDIA RTX 5070 Ti | AMD Strix Halo 128GB |
|---|---|---|
| Gemma 4 26B · 4B active | 130.3 t/sQ3_K_S | 9.5 t/sFP16 |
| Qwen3.8 27B | 58.4 t/sQ2_K | 3.5 t/sFP16 |
| Qwen3.8 125B · 6B active | doesn't fit at these settings | 12.6 t/sQ6_K |
| Qwen3.6 35B · 3B active | 193.2 t/sQ2_K | 12.6 t/sFP16 |
| DeepSeek V4 Flash 284B · 13B active | doesn't fit at these settings | 33.5 t/sQ2_K |
| Qwen3.6 27B | 58.4 t/sQ2_K | 3.5 t/sFP16 |
| DeepSeek V4.1 Flash 552B · 16B active | doesn't fit at these settings | doesn't fit at these settings |
Change the context, RAM or model in the calculator: NVIDIA RTX 5070 Ti · AMD Strix Halo 128GB
Every report on each card, with its source: NVIDIA RTX 5070 Ti · AMD Strix Halo 128GB