Intel Arc Pro B70 vs NVIDIA L4 for local LLMs
17 reports on the Intel Arc Pro B70 and 3 on the NVIDIA L4
Which is faster for local LLMs?
On Qwen3.8 27B at 4-bit, the Intel Arc Pro B70 has 25.6 generation tokens/s (one run); prompt processing 512.1 tokens/s (one run); the NVIDIA L4 has 14.6 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 2.0x higher on the Intel Arc Pro B70 (608 GB/s on the Intel Arc Pro B70, 300 on the NVIDIA L4).
- Memory
- 32GB
- Memory bandwidth
- 608 GB/s
- FP16 compute
- 183.5 TFLOPS
- Reports
- 17
- Memory
- 24GB
- Memory bandwidth
- 300 GB/s
- FP16 compute
- 121 TFLOPS
- Reports
- 3
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 L4 |
|---|---|---|
| Qwen3.8 27B4-bit | 25.6one runPP 512.1 (one run)llama.cppcontext not stated | 14.6one runllama.cppcontext 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 L4 |
|---|---|---|
| Qwen3.8 27B | 15.2 t/sQ6_K | 10.9 t/sQ4_K_M |
| Qwen3.8 125B · 6B active | 18.6 t/sQ2_K, experts in RAM | 16.4 t/sQ2_K, experts in RAM |
| Qwen3.6 35B · 3B active | 55.3 t/sQ5_K_M | 38.5 t/sQ4_K_S |
| 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 | 10.9 t/sQ4_K_M |
| Gemma 4 26B · 4B active | 38.8 t/sQ6_K | 24.5 t/sQ5_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 Pro B70 · NVIDIA L4
Every report on each card, with its source: Intel Arc Pro B70 · NVIDIA L4