Intel Arc A770 16GB vs AMD RX 9070 for local LLMs
4 reports on the Intel Arc A770 16GB and 7 on the AMD RX 9070
Which is faster for local LLMs?
On Qwen3.8 27B at 3-bit, the Intel Arc A770 16GB has 12.0 generation tokens/s (one run); the AMD RX 9070 has generation speed not reported; prompt processing 600.0 tokens/s (one run). Memory bandwidth, which caps how fast a card can write, is 14% higher on the AMD RX 9070 (560 GB/s on the Intel Arc A770 16GB, 640 on the AMD RX 9070).
- Memory
- 16GB
- Memory bandwidth
- 560 GB/s
- FP16 compute
- 39.3 TFLOPS
- Reports
- 4
- Memory
- 16GB
- Memory bandwidth
- 640 GB/s
- FP16 compute
- 145 TFLOPS
- Reports
- 7
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 | Intel Arc A770 16GB | AMD RX 9070 |
|---|---|---|
| Qwen3.8 27B3-bit | 12.0one runengine not statedcontext not stated | -0 runsPP 600.0 (one run)llama.cpp128K 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 | Intel Arc A770 16GB | AMD RX 9070 |
|---|---|---|
| Qwen3.8 27B | 36.5 t/sQ2_K | 41.7 t/sQ2_K |
| Qwen3.8 125B · 6B active | doesn't fit at these settings | doesn't fit at these settings |
| DeepSeek V4 Flash 284B · 13B active | doesn't fit at these settings | doesn't fit at these settings |
| Qwen3.6 35B · 3B active | 120.8 t/sQ2_K | 138.0 t/sQ2_K |
| Qwen3.6 27B | 36.5 t/sQ2_K | 41.7 t/sQ2_K |
| Gemma 4 26B · 4B active | 81.4 t/sQ3_K_S | 93.0 t/sQ3_K_S |
| GLM-5.3 320B · 18B active | doesn't fit at these settings | doesn't fit at these settings |
Change the context, RAM or model in the calculator: Intel Arc A770 16GB · AMD RX 9070
Every report on each card, with its source: Intel Arc A770 16GB · AMD RX 9070