Intel Arc B580 12GB vs Intel Arc Pro B60 24GB for local LLMs
5 reports on the Intel Arc B580 12GB and 5 on the Intel Arc Pro B60 24GB
Which is faster for local LLMs?
Nobody has reported the same model at the same quant on both cards yet, so there's no measured head-to-head. Memory bandwidth, which caps how fast a card can write, is about the same on both (456 GB/s on the Intel Arc B580 12GB, 456 on the Intel Arc Pro B60 24GB). The estimates below compare them on the models people run most.
- Memory
- 12GB
- Memory bandwidth
- 456 GB/s
- FP16 compute
- 117 TFLOPS
- Reports
- 5
- Memory
- 24GB
- Memory bandwidth
- 456 GB/s
- FP16 compute
- 98.5 TFLOPS
- Reports
- 5
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.
| Model | Intel Arc B580 12GB | Intel Arc Pro B60 24GB |
|---|---|---|
| Qwen3.8 27B | 1.6 t/sQ8_0, layers on CPU | 16.5 t/sQ4_K_M |
| Qwen3.8 125B · 6B active | doesn't fit at these settings | 17.8 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 35B · 3B active | 13.7 t/sQ6_K, experts in RAM | 58.5 t/sQ4_K_S |
| Qwen3.6 27B | 1.6 t/sQ8_0, layers on CPU | 16.5 t/sQ4_K_M |
| Gemma 4 26B · 4B active | 74.5 t/sQ2_K | 37.2 t/sQ5_K_S |
Change the context, RAM or model in the calculator: Intel Arc B580 12GB · Intel Arc Pro B60 24GB
Every report on each card, with its source: Intel Arc B580 12GB · Intel Arc Pro B60 24GB