Intel Arc B580
12 GB · 456 GB/s · 190 W
Prices
Every retailer we track in the US, cheapest first. Buy links may earn us a commission.
No retailer in this market lists it right now.
What two of them run
Every model in the catalogue, with the best quant for this hardware. Estimates, not measurements.
| Model | Quant | Fits | Memory | Max context | Decode @8k | Prefill | Good for |
|---|---|---|---|---|---|---|---|
| Qwen 3.8 27B Alibaba Qwen | UD-Q5_K_M | fits | 20.4 GB | 37k65k with q8 cache | 11tok/sest. | 611 tok/s | – |
| Qwen 3.6 27B Alibaba Qwen | Q5_K_M | fits | 20.2 GB | 40k71k with q8 cache | 11tok/sest. | 611 tok/s | – |
| Gemma 4 31B | Q4_K_M | fits | 19.8 GB | 38k76k with q8 cache | 12tok/sest. | 533 tok/s | – |
| Qwen 3.6 35B-A3B Alibaba Qwen | UD-Q4_K_M | fits | 22.2 GB | 16k26k with q8 cache | 60tok/sest. | 5239 tok/s | chat, coding, agents, long documents |
| Qwen 3.5 27B Alibaba Qwen | Q5_K_M | fits | 20.2 GB | 39k69k with q8 cache | 11tok/sest. | 611 tok/s | – |
| Gemma 4 26B-A4B | UD-Q5_K_M | fits | 21.4 GB | 47k79k with q8 cache | 34tok/sest. | 3992 tok/s | chat, coding, agents, long documents |
| Qwen 3.5 35B-A3B Alibaba Qwen | Q4_K_M | fits | 22.1 GB | 21k33k with q8 cache | 61tok/sest. | 5239 tok/s | chat, coding, agents, long documents |
| GLM 4.7 Flash Z.ai | Q5_K_M | fits | 21.7 GB | 20k34k with q8 cache | 31tok/sest. | 2932 tok/s | chat, coding |
| Devstral Small 2 24B Mistral AI | Q6_K | fits | 20.6 GB | 19k34k with q8 cache | 11tok/sest. | 689 tok/s | – |
| gpt-oss 20B OpenAI | MXFP4 | fits | 12.8 GB | 128k | 48tok/sest. | 3792 tok/s | chat, coding, agents, long documents |
| Qwen3 Coder 30B-A3B Alibaba Qwen | Q5_K_M | fits | 22.3 GB | 8k15k with q8 cache | 43tok/sest. | 3790 tok/s | chat |
| Qwen3 32B Alibaba Qwen | Q4_K_M | fits | 21.8 GB | 10k19k with q8 cache | 10tok/sest. | 472 tok/s | – |
| Gemma 4 12B | Q8_0 | fits | 13.6 GB | 256k | 17tok/sest. | 1391 tok/s | chat, long documents |
| Qwen 3.5 9B Alibaba Qwen | Q8_0 | fits | 10.5 GB | 256k | 23tok/sest. | 1761 tok/s | chat, coding, long documents |
| Gemma 3 27B | Q5_K_M | fits | 20.3 GB | 32k61k with q8 cache | 11tok/sest. | 620 tok/s | – |
| Mistral Small 3.2 24B Mistral AI | Q6_K | fits | 20.6 GB | 19k34k with q8 cache | 11tok/sest. | 689 tok/s | – |
| DeepSeek R1 Distill Qwen 32B DeepSeek | Q4_K_M | fits | 21.8 GB | 10k18k with q8 cache | 10tok/sest. | 493 tok/s | – |
| Ministral 3 14B Mistral AI | Q8_0 | fits | 16.0 GB | 47k86k with q8 cache | 15tok/sest. | 1143 tok/s | – |
| Qwen3 14B Alibaba Qwen | Q8_0 | fits | 17.2 GB | 39k40k with q8 cache | 13tok/sest. | 1063 tok/s | – |
| DeepSeek R1 0528 Qwen3 8B DeepSeek | Q8_0 | fits | 10.6 GB | 88k128k with q8 cache | 23tok/sest. | 1859 tok/s | chat |
| Qwen3 8B Alibaba Qwen | Q8_0 | fits | 10.6 GB | 40k | 23tok/sest. | 1859 tok/s | chat |
| Phi-4 14B Microsoft | Q8_0 | fits | 17.4 GB | 16k | 13tok/sest. | 1070 tok/s | – |
| Qwen 3.5 4B Alibaba Qwen | Q8_0 | fits | 5.8 GB | 256k | 48tok/sest. | 3546 tok/s | chat, coding, long documents |
| Ministral 3 8B Mistral AI | Q8_0 | fits | 10.8 GB | 91k166k with q8 cache | 22tok/sest. | 1737 tok/s | chat |
| Granite 4.2 8B IBM | Q8_0 | fits | 11.3 GB | 76k128k with q8 cache | 21tok/sest. | 1724 tok/s | chat |
| Gemma 4 E4B | Q8_0 | fits | 9.2 GB | 128k | 27tok/sest. | 2135 tok/s | chat, coding, long documents |
| LFM2.5 8B-A1B Liquid AI | Q8_0 | fits | 10.1 GB | 125k | 86tok/sest. | 12459 tok/s | chat, coding, long documents |
| Llama 3.1 8B Meta | Q6_K | fits | 8.5 GB | 114k128k with q8 cache | 30tok/sest. | 1920 tok/s | chat, coding |
| Qwen 3.5 122B-A10B Alibaba Qwen | UD-Q2_K_XL | offload | 40.6 GB | – | 14tok/sest. | 1167 tok/s | – |
| Qwen3 Coder Next Alibaba Qwen | Q4_K_M | offload | 46.8 GB | – | 17tok/sest. | 2769 tok/s | chat |
| Mistral Small 4 119B Mistral AI | UD-Q2_K_XL | offload | 39.0 GB | – | 20tok/sest. | 1555 tok/s | chat |
| GLM 4.5 Air Z.ai | Q2_K | offload | 45.0 GB | – | 6tok/sest. | 556 tok/s | – |
| Qwen3 Next 80B-A3B Alibaba Qwen | Q4_K_M | offload | 46.8 GB | – | 22tok/sest. | 3482 tok/s | chat |
| Nemotron 3.5 Lightning 30B-A3B NVIDIA | UD-Q6_K_XL | offload | 34.0 GB | – | 17tok/sest. | 4293 tok/s | chat |
| Kimi Linear 48B-A3B Moonshot AI | Q4_K_M | offload | 29.4 GB | – | 36tok/sest. | 4230 tok/s | chat, coding, long documents |
| Llama 3.3 70B Meta | Q4_K_M | offload | 43.4 GB | – | 2tok/sest. | 161 tok/s | – |
| DeepSeek V4 Flash DeepSeek | UD-Q2_K_XL | won't run | 92.2 GB | – | – | – | – |
| GLM 5.3 Flash Z.ai | UD-Q2_K_XL | won't run | 102.8 GB | – | – | – | – |
| Qwen 3.8 Flash Next Alibaba Qwen | UD-Q2_K_XL | won't run | 75.1 GB | – | – | – | – |
| MiniMax M2.7 MiniMax | UD-Q2_K_XL | won't run | 73.4 GB | – | – | – | – |
| Nemotron 3 Super 120B-A12B NVIDIA | UD-Q2_K_XL | won't run | 52.5 GB | – | – | – | – |
| gpt-oss 120B OpenAI | MXFP4 | won't run | 60.7 GB | – | – | – | – |
Specifications
From the manufacturer's published specifications; sources are linked where we have them.
- GPU
- Arc B580
- Memory
- 12 GB GDDR6
- Memory bus
- 192-bit
- Memory bandwidth
- 456 GB/s
- FP16 compute
- 116.5 TFLOPS
- Software
- SYCL / oneAPI
- Board power
- 190 W
- PCIe generation
- Gen 4
- PCIe lanes
- x8