Intel Arc B580 12GB vs NVIDIA RTX 4070 Ti for local LLMs
5 reports on the Intel Arc B580 12GB and 1 on the NVIDIA RTX 4070 Ti
Which is faster for local LLMs?
On Qwen3.8 27B at 2-bit, the Intel Arc B580 12GB runs at 0.7 tokens per second (one run) and the NVIDIA RTX 4070 Ti at 43.6 (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 11% higher on the NVIDIA RTX 4070 Ti (456 GB/s on the Intel Arc B580 12GB, 504 on the NVIDIA RTX 4070 Ti).
- Memory
- 12GB
- Memory bandwidth
- 456 GB/s
- FP16 compute
- 117 TFLOPS
- Reports
- 5
- Memory
- 12GB
- Memory bandwidth
- 504 GB/s
- FP16 compute
- 160 TFLOPS
- Reports
- 1
Measured on both
Median tokens per second 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 quant level. Engines and context lengths can still differ between the runs. How to read these
| Model | Intel Arc B580 12GB | NVIDIA RTX 4070 Ti |
|---|---|---|
| Qwen3.8 27B2-bit | 0.7one run | 43.6one run |
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 B580 12GB | NVIDIA RTX 4070 Ti |
|---|---|---|
| Qwen3.8 27B | 1.6 t/sQ8_0, layers on CPU | 1.7 t/sQ8_0, layers on CPU |
| 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 | 13.7 t/sQ6_K, experts in RAM | 13.9 t/sQ6_K, experts in RAM |
| Qwen3.6 27B | 1.6 t/sQ8_0, layers on CPU | 1.7 t/sQ8_0, layers on CPU |
| Gemma 4 26B · 4B active | 74.5 t/sQ2_K | 82.3 t/sQ2_K |
| 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: Intel Arc B580 12GB · NVIDIA RTX 4070 Ti
Every report on each card, with its source: Intel Arc B580 12GB · NVIDIA RTX 4070 Ti