Intel Arc Pro B60 24GB vs NVIDIA L4 for local LLMs
7 reports on the Intel Arc Pro B60 24GB and 3 on the NVIDIA L4
Which is faster for local LLMs?
On Qwen3.8 27B at 4-bit, the Intel Arc Pro B60 24GB has 22.0 generation tokens/s (3 runs); prompt processing 379.5 tokens/s (2 runs); 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 1.5x higher on the Intel Arc Pro B60 24GB (456 GB/s on the Intel Arc Pro B60 24GB, 300 on the NVIDIA L4).
- Memory
- 24GB
- Memory bandwidth
- 456 GB/s
- FP16 compute
- 98.5 TFLOPS
- Reports
- 7
- 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 B60 24GB | NVIDIA L4 |
|---|---|---|
| Qwen3.8 27B4-bit | 22.03 runsPP 379.5 (2 runs)llama.cpp, 1 not stated512 to 150K context | 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 B60 24GB | NVIDIA L4 |
|---|---|---|
| Qwen3.8 27B | 16.5 t/sQ4_K_M | 10.9 t/sQ4_K_M |
| Qwen3.8 125B · 6B active | 17.8 t/sQ2_K, experts in RAM | 16.4 t/sQ2_K, experts in RAM |
| Qwen3.6 35B · 3B active | 58.5 t/sQ4_K_S | 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 | 16.5 t/sQ4_K_M | 10.9 t/sQ4_K_M |
| Gemma 4 26B · 4B active | 37.2 t/sQ5_K_S | 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 B60 24GB · NVIDIA L4
Every report on each card, with its source: Intel Arc Pro B60 24GB · NVIDIA L4