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 @64k | Prefill | Good for |
|---|---|---|---|---|---|---|---|
| Qwen 3.8 27B Alibaba Qwen | UD-Q4_K_M | fits | 21.1 GB | 82k144k with q8 cache | 11tok/sest. | 511 tok/s | – |
| Qwen 3.6 27B Alibaba Qwen | Q4_K_M | fits | 21.5 GB | 77k135k with q8 cache | 11tok/sest. | 511 tok/s | – |
| Qwen 3.5 27B Alibaba Qwen | Q4_K_M | fits | 21.4 GB | 78k137k with q8 cache | 11tok/sest. | 511 tok/s | – |
| Gemma 4 26B-A4B | UD-Q4_K_M | fits | 18.9 GB | 201k256k with q8 cache | 30tok/sest. | 3148 tok/s | chat, coding, agents, long documents |
| GLM 4.7 Flash Z.ai | Q4_K_M | fits | 22.0 GB | 70k121k with q8 cache | 19tok/sest. | 1525 tok/s | chat, coding |
| gpt-oss 20B OpenAI | MXFP4 | fits | 14.5 GB | 128k | 31tok/sest. | 2353 tok/s | chat, coding, agents, long documents |
| Gemma 4 12B | Q8_0 | fits | 14.8 GB | 256k | 16tok/sest. | 1210 tok/s | chat, long documents |
| Qwen 3.5 9B Alibaba Qwen | Q8_0 | fits | 12.6 GB | 256k | 19tok/sest. | 1481 tok/s | chat, coding, long documents |
| Qwen3 14B Alibaba Qwen | Q5_K_M | fits | 21.5 GB | 40k | 11tok/sest. | 620 tok/s | chat |
| Ministral 3 14B Mistral AI | Q6_K | fits | 22.0 GB | 66k121k with q8 cache | 10tok/sest. | 708 tok/s | chat |
| DeepSeek R1 0528 Qwen3 8B DeepSeek | Q8_0 | fits | 18.8 GB | 88k128k with q8 cache | 12tok/sest. | 979 tok/s | chat |
| Qwen3 8B Alibaba Qwen | Q8_0 | fits | 18.8 GB | 40k | 12tok/sest. | 979 tok/s | chat |
| Qwen 3.5 4B Alibaba Qwen | Q8_0 | fits | 7.9 GB | 256k | 34tok/sest. | 2567 tok/s | chat, coding, long documents |
| Ministral 3 8B Mistral AI | Q8_0 | fits | 18.6 GB | 91k166k with q8 cache | 13tok/sest. | 968 tok/s | chat |
| Granite 4.2 8B IBM | Q8_0 | fits | 20.4 GB | 76k128k with q8 cache | 11tok/sest. | 895 tok/s | chat |
| Gemma 4 E4B | Q8_0 | fits | 11.1 GB | 128k | 23tok/sest. | 1940 tok/s | chat, coding, long documents |
| LFM2.5 8B-A1B Liquid AI | Q8_0 | fits | 13.1 GB | 125k | 29tok/sest. | 4140 tok/s | chat, coding, long documents |
| Llama 3.1 8B Meta | Q6_K | fits | 15.8 GB | 114k128k with q8 cache | 15tok/sest. | 1051 tok/s | chat, coding |
| Qwen 3.5 122B-A10B Alibaba Qwen | UD-Q2_K_XL | offload | 42.3 GB | – | 10tok/sest. | 751 tok/s | – |
| Gemma 4 31B | Q4_K_M | offload | 24.5 GB | 38k76k with q8 cache | 7tok/sest. | 440 tok/s | – |
| Mistral Small 4 119B Mistral AI | UD-Q2_K_XL | offload | 40.5 GB | – | 13tok/sest. | 752 tok/s | chat |
| Qwen 3.6 35B-A3B Alibaba Qwen | UD-Q4_K_M | offload | 23.6 GB | 16k26k with q8 cache | 33tok/sest. | 2973 tok/s | chat, coding, agents, long documents |
| Qwen 3.5 35B-A3B Alibaba Qwen | Q4_K_M | offload | 23.5 GB | 21k33k with q8 cache | 33tok/sest. | 2982 tok/s | chat, coding, agents, long documents |
| Devstral Small 2 24B Mistral AI | Q4_K_M | offload | 25.0 GB | 47k87k with q8 cache | 7tok/sest. | 469 tok/s | – |
| Nemotron 3.5 Lightning 30B-A3B NVIDIA | UD-Q6_K_XL | offload | 34.7 GB | – | 15tok/sest. | 2943 tok/s | chat |
| Kimi Linear 48B-A3B Moonshot AI | Q4_K_M | offload | 30.2 GB | – | 28tok/sest. | 2064 tok/s | chat, coding, long documents |
| Qwen3 Coder 30B-A3B Alibaba Qwen | Q4_K_M | offload | 25.0 GB | 38k68k with q8 cache | 11tok/sest. | 1028 tok/s | chat, coding |
| Qwen3 32B Alibaba Qwen | Q4_K_M | offload | 36.1 GB | 10k19k with q8 cache | 3tok/sest. | 198 tok/s | – |
| Gemma 3 27B | Q4_K_M | offload | 22.5 GB | 62k115k with q8 cache | 10tok/sest. | 570 tok/s | – |
| Mistral Small 3.2 24B Mistral AI | Q4_K_M | offload | 25.0 GB | 47k87k with q8 cache | 7tok/sest. | 469 tok/s | – |
| DeepSeek R1 Distill Qwen 32B DeepSeek | Q4_K_M | offload | 36.2 GB | 10k18k with q8 cache | 3tok/sest. | 245 tok/s | – |
| Phi-4 14B Microsoft | Q4_K_M | offload | 22.5 GB | 16k | 10tok/sest. | 621 tok/s | chat |
| DeepSeek V4 Flash DeepSeek | UD-Q2_K_XL | won't run | 97.2 GB | – | – | – | – |
| GLM 5.3 Flash Z.ai | UD-Q2_K_XL | won't run | 103.7 GB | – | – | – | – |
| Qwen 3.8 Flash Next Alibaba Qwen | UD-Q2_K_XL | won't run | 76.7 GB | – | – | – | – |
| MiniMax M2.7 MiniMax | UD-Q2_K_XL | won't run | 87.3 GB | – | – | – | – |
| Nemotron 3 Super 120B-A12B NVIDIA | UD-Q2_K_XL | won't run | 53.2 GB | – | – | – | – |
| Qwen3 Coder Next Alibaba Qwen | Q4_K_M | won't run | 48.4 GB | – | – | – | – |
| gpt-oss 120B OpenAI | MXFP4 | won't run | 63.0 GB | – | – | – | – |
| GLM 4.5 Air Z.ai | Q2_K | won't run | 55.4 GB | – | – | – | – |
| Qwen3 Next 80B-A3B Alibaba Qwen | Q4_K_M | won't run | 48.4 GB | – | – | – | – |
| Llama 3.3 70B Meta | Q4_K_M | won't run | 61.3 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