Intel Arc Pro B70 vs NVIDIA RTX 5090 for local LLMs
19 reports on the Intel Arc Pro B70 and 161 on the NVIDIA RTX 5090
Which is faster for local LLMs?
On Qwen3.6 35B · 3B active at 4-bit, the Intel Arc Pro B70 has 63.7 generation tokens/s (5 runs); prompt processing 977.4 tokens/s (4 runs); the NVIDIA RTX 5090 has 215.1 generation tokens/s (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 2.9x higher on the NVIDIA RTX 5090 (608 GB/s on the Intel Arc Pro B70, 1,792 on the NVIDIA RTX 5090). Across 2 shared models with generation measurements on both cards, the Intel Arc Pro B70's median is higher on 0 and the NVIDIA RTX 5090's on 2.
- Memory
- 32GB
- Memory bandwidth
- 608 GB/s
- FP16 compute
- 183.5 TFLOPS
- Reports
- 19
- Memory
- 32GB
- Memory bandwidth
- 1,792 GB/s
- FP16 compute
- 419 TFLOPS
- Reports
- 161
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 Pro B70 | NVIDIA RTX 5090 |
|---|---|---|
| Qwen3.6 35B · 3B active4-bit | 63.75 runsPP 977.4 (4 runs)llama.cpp127K to 256K context, 2 not stated | 215.1one runllama.cppcontext not stated |
| Qwen3.8 27B4-bit | 25.6one runPP 512.1 (one run)llama.cppcontext not stated | 73.25 runsllama.cpp, vLLM, 2 not stated120K to 256K context, 2 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 | Intel Arc Pro B70 | NVIDIA RTX 5090 |
|---|---|---|
| Qwen3.6 35B · 3B active | 55.3 t/sQ5_K_M | 163.0 t/sQ5_K_M |
| Qwen3.8 27B | 15.2 t/sQ6_K | 44.9 t/sQ6_K |
| Qwen3.8 125B · 6B active | 18.6 t/sQ2_K, experts in RAM | 20.3 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 | 44.9 t/sQ6_K |
| Gemma 4 26B · 4B active | 38.8 t/sQ6_K | 114.5 t/sQ6_K |
| GLM-5.3 320B · 18B active | doesn't fit at these settings | doesn't fit at these settings |
| 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 5090
Every report on each card, with its source: Intel Arc Pro B70 · NVIDIA RTX 5090