Intel Arc B580 12GB vs M1 Ultra 128GB for local LLMs
10 reports on the Intel Arc B580 12GB and 11 on the M1 Ultra 128GB
Which is faster for local LLMs?
On Qwen3 4B at 4-bit, the Intel Arc B580 12GB has 12.7 generation tokens/s (one run); prompt processing 260.5 tokens/s (one run); the M1 Ultra 128GB has 116.9 generation tokens/s (one run); prompt processing 942.3 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 1.8x higher on the M1 Ultra 128GB (456 GB/s on the Intel Arc B580 12GB, 819 on the M1 Ultra 128GB).
- Memory
- 12GB
- Memory bandwidth
- 456 GB/s
- FP16 compute
- 117 TFLOPS
- Reports
- 10
- Memory
- 128GB unified
- Memory bandwidth
- 819 GB/s
- FP16 compute
- 21 TFLOPS
- Reports
- 11
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 B580 12GB | M1 Ultra 128GB |
|---|---|---|
| Qwen3 4B4-bit | 12.7one runPP 260.5 (one run)llama.cppcontext not stated | 116.9one runPP 942.3 (one run)engine not statedcontext 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 B580 12GB | M1 Ultra 128GB |
|---|---|---|
| Qwen3 4B | 77.2 t/sQ6_K | 50.4 t/sFP16 |
| Qwen3.8 27B | 1.6 t/sQ8_0, layers on CPU | 7.5 t/sFP16 |
| Qwen3.8 125B · 6B active | doesn't fit at these settings | 34.0 t/sQ5_K_S |
| Qwen3.6 35B · 3B active | 13.7 t/sQ6_K, experts in RAM | 23.5 t/sFP16 |
| DeepSeek V4 Flash 284B · 13B active | doesn't fit at these settings | 53.5 t/sQ2_K |
| Qwen3.6 27B | 1.6 t/sQ8_0, layers on CPU | 7.5 t/sFP16 |
| Gemma 4 26B · 4B active | 74.5 t/sQ2_K | 20.2 t/sFP16 |
Change the context, RAM or model in the calculator: Intel Arc B580 12GB · M1 Ultra 128GB
Every report on each card, with its source: Intel Arc B580 12GB · M1 Ultra 128GB