Intel Arc Pro B70 vs NVIDIA RTX 2080 Ti 22GB (modded) for local LLMs
14 reports on the Intel Arc Pro B70 and 7 on the NVIDIA RTX 2080 Ti 22GB (modded)
Which is faster for local LLMs?
On Qwen3.6 35B · 3B active at 4-bit, the Intel Arc Pro B70 runs at 63.7 tokens per second (5 runs) and the NVIDIA RTX 2080 Ti 22GB (modded) at 69.0 (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 about the same on both (608 GB/s on the Intel Arc Pro B70, 616 on the NVIDIA RTX 2080 Ti 22GB (modded)).
- Memory
- 32GB
- Memory bandwidth
- 608 GB/s
- FP16 compute
- 183.5 TFLOPS
- Reports
- 14
- Memory
- 22GB
- Memory bandwidth
- 616 GB/s
- FP16 compute
- 108 TFLOPS
- Reports
- 7
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 Pro B70 | NVIDIA RTX 2080 Ti 22GB (modded) |
|---|---|---|
| Qwen3.6 35B · 3B active4-bit | 63.75 runs | 69.0one 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 Pro B70 | NVIDIA RTX 2080 Ti 22GB (modded) |
|---|---|---|
| Qwen3.6 35B · 3B active | 55.3 t/sQ5_K_M | 93.6 t/sQ3_K_M |
| Qwen3.8 27B | 15.2 t/sQ6_K | 25.1 t/sQ4_K_S |
| Qwen3.8 125B · 6B active | 18.6 t/sQ2_K, experts in RAM | 18.6 t/sQ2_K, experts in RAM |
| DeepSeek V4 Flash 284B · 13B active | doesn't fit at these settings | doesn't fit at these settings |
| Qwen3.6 27B | 15.2 t/sQ6_K | 25.1 t/sQ4_K_S |
| Gemma 4 26B · 4B active | 38.8 t/sQ6_K | 56.6 t/sQ4_K_M |
| 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 Pro B70 · NVIDIA RTX 2080 Ti 22GB (modded)
Every report on each card, with its source: Intel Arc Pro B70 · NVIDIA RTX 2080 Ti 22GB (modded)