Intel Arc B580
12 GB · 456 GB/s · 190 W
Prices
Every retailer we track in India, cheapest first. Buy links may earn us a commission.
No retailer in this market lists it right now.
What it runs
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 |
|---|---|---|---|---|---|---|---|
| Gemma 4 12B | Q5_K_M | fits | 10.3 GB | 104k169k with q8 cache | 23tok/sest. | 1210 tok/s | chat, coding, long documents |
| Qwen 3.5 9B Alibaba Qwen | Q6_K | fits | 10.2 GB | 91k151k with q8 cache | 24tok/sest. | 1481 tok/s | chat, coding |
| Qwen 3.5 4B Alibaba Qwen | Q8_0 | fits | 7.4 GB | 166k256k with q8 cache | 34tok/sest. | 2567 tok/s | chat, coding, long documents |
| Gemma 4 E4B | Q8_0 | fits | 10.6 GB | 82k128k with q8 cache | 23tok/sest. | 1940 tok/s | chat, coding |
| LFM2.5 8B-A1B Liquid AI | UD-Q6_K | fits | 10.8 GB | 72k123k with q8 cache | 31tok/sest. | 4140 tok/s | chat, coding |
| Qwen 3.8 27B Alibaba Qwen | UD-Q4_K_M | offload | 20.6 GB | – | 4tok/sest. | 362 tok/s | – |
| Qwen 3.6 27B Alibaba Qwen | Q4_K_M | offload | 21.0 GB | – | 4tok/sest. | 359 tok/s | – |
| Gemma 4 31B | Q4_K_M | offload | 24.0 GB | – | 3tok/sest. | 309 tok/s | – |
| Qwen 3.6 35B-A3B Alibaba Qwen | UD-Q4_K_M | offload | 23.1 GB | – | 14tok/sest. | 2073 tok/s | chat |
| Qwen 3.5 27B Alibaba Qwen | Q4_K_M | offload | 20.9 GB | – | 4tok/sest. | 360 tok/s | – |
| Gemma 4 26B-A4B | UD-Q4_K_M | offload | 18.4 GB | – | 13tok/sest. | 2358 tok/s | chat |
| Qwen 3.5 35B-A3B Alibaba Qwen | Q4_K_M | offload | 23.0 GB | – | 14tok/sest. | 2077 tok/s | chat |
| GLM 4.7 Flash Z.ai | Q4_K_M | offload | 21.5 GB | – | 7tok/sest. | 1061 tok/s | chat |
| Devstral Small 2 24B Mistral AI | Q4_K_M | offload | 24.5 GB | – | 3tok/sest. | 331 tok/s | – |
| Nemotron 3.5 Lightning 30B-A3B NVIDIA | UD-Q6_K_XL | offload | 34.2 GB | – | 10tok/sest. | 2207 tok/s | – |
| gpt-oss 20B OpenAI | MXFP4 | offload | 14.0 GB | – | 18tok/sest. | 2049 tok/s | chat, coding |
| Kimi Linear 48B-A3B Moonshot AI | Q4_K_M | offload | 29.7 GB | – | 17tok/sest. | 1508 tok/s | chat |
| Qwen3 Coder 30B-A3B Alibaba Qwen | Q4_K_M | offload | 24.5 GB | – | 5tok/sest. | 724 tok/s | chat |
| Qwen3 32B Alibaba Qwen | Q4_K_M | offload | 35.6 GB | – | 2tok/sest. | 150 tok/s | – |
| Gemma 3 27B | Q4_K_M | offload | 22.0 GB | – | 4tok/sest. | 394 tok/s | – |
| Mistral Small 3.2 24B Mistral AI | Q4_K_M | offload | 24.5 GB | – | 3tok/sest. | 331 tok/s | – |
| DeepSeek R1 Distill Qwen 32B DeepSeek | Q4_K_M | offload | 35.7 GB | – | 2tok/sest. | 185 tok/s | – |
| Ministral 3 14B Mistral AI | Q4_K_M | offload | 18.8 GB | 16k30k with q8 cache | 5tok/sest. | 524 tok/s | chat |
| Qwen3 14B Alibaba Qwen | Q4_K_M | offload | 19.6 GB | 12k22k with q8 cache | 5tok/sest. | 451 tok/s | chat |
| DeepSeek R1 0528 Qwen3 8B DeepSeek | Q4_K_M | offload | 14.9 GB | 39k70k with q8 cache | 8tok/sest. | 822 tok/s | chat, coding |
| Qwen3 8B Alibaba Qwen | Q4_K_M | offload | 14.9 GB | 39k40k with q8 cache | 8tok/sest. | 822 tok/s | chat, coding |
| Phi-4 14B Microsoft | Q4_K_M | offload | 22.0 GB | 10k16k with q8 cache | 4tok/sest. | 429 tok/s | chat |
| Ministral 3 8B Mistral AI | Q4_K_M | offload | 14.5 GB | 40k72k with q8 cache | 9tok/sest. | 824 tok/s | chat, coding |
| Granite 4.2 8B IBM | Q4_K_M | offload | 16.3 GB | 32k58k with q8 cache | 7tok/sest. | 713 tok/s | chat, coding |
| Llama 3.1 8B Meta | Q4_K_M | offload | 13.8 GB | 44k80k with q8 cache | 10tok/sest. | 923 tok/s | chat, coding |
| DeepSeek V4 Flash DeepSeek | UD-Q2_K_XL | won't run | 96.7 GB | – | – | – | – |
| GLM 5.3 Flash Z.ai | UD-Q2_K_XL | won't run | 103.2 GB | – | – | – | – |
| Qwen 3.8 Flash Next Alibaba Qwen | UD-Q2_K_XL | won't run | 76.2 GB | – | – | – | – |
| MiniMax M2.7 MiniMax | UD-Q2_K_XL | won't run | 86.8 GB | – | – | – | – |
| Qwen 3.5 122B-A10B Alibaba Qwen | UD-Q2_K_XL | won't run | 41.8 GB | – | – | – | – |
| Nemotron 3 Super 120B-A12B NVIDIA | UD-Q2_K_XL | won't run | 52.7 GB | – | – | – | – |
| Qwen3 Coder Next Alibaba Qwen | Q4_K_M | won't run | 47.9 GB | – | – | – | – |
| gpt-oss 120B OpenAI | MXFP4 | won't run | 62.5 GB | – | – | – | – |
| Mistral Small 4 119B Mistral AI | UD-Q2_K_XL | won't run | 40.0 GB | – | – | – | – |
| GLM 4.5 Air Z.ai | Q2_K | won't run | 54.9 GB | – | – | – | – |
| Qwen3 Next 80B-A3B Alibaba Qwen | Q4_K_M | won't run | 47.9 GB | – | – | – | – |
| Llama 3.3 70B Meta | Q4_K_M | won't run | 60.8 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