Intel Arc B580
12 GB · 456 GB/s · 190 W
In short
The Intel Arc B580 has 12 GB of GDDR6 memory with 456 GB/s of bandwidth, which sets how fast it generates text. At 8k context it runs 27 of the 113 open models we track fully in memory; the most capable is Gemma 4 12B at Q6_K, at about 22 tok/s (estimated). The best new price for the Intel Arc B580 in Germany is 360 € at Amazon; used, it starts at 330 € (asking price).
Updated . Speeds are estimates; how they are worked out.
Prices
Every retailer we track in Germany, cheapest first. Buy links may earn us a commission.
| Retailer | Condition | Price | Stock | Checked | Buy |
|---|---|---|---|---|---|
| eBayASRock Arc B580 Challenger 12GB OC | used, asking price | 330 €+ 8 € delivery | In stock | 2 h ago | Buy |
| eBayASRock Intel Arc B580 Steel Legend Gaming OC Grafikkarte 12GB GDDR6 weiß | used, asking price | 350 €+ 6 € delivery | In stock | 2 h ago | Buy |
| AmazonIntel Arc B580 Limited Edition Graphics Card | New | 360 € | In stock | 7 h ago | Buy |
| eBayASRock Arc B580 Challenger 12GB OC | New | 366 € | In stock | 2 h ago | Buy |
| AmazonSparkle Technology Intel Arc B580 Titan Oc 12 GB Gddr6 | New | 405 € | In stock | 46 min ago | Buy |
| eBaySparkle Intel Arc B580 TITAN OC SB580T-12GOC 12GB GDDR6 1x HDMI 3x DP | New | 500 €+ 9 € delivery | In stock | 2 h ago | Buy |
| eBaySparkle Arc B580 Guardian | New | 621 €+ 18 € delivery | In stock | 2 h ago | Buy |
Price history
Lowest price shown each day over the last 90 days.
Not enough price history yet.
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 @8k | Prefill | Good for |
|---|---|---|---|---|---|---|---|
| Gemma 4 12B | Q6_K | fits | 10.4 GB | 45k79k with q8 cache | 22tok/sest. | 1391 tok/s | chat, coding |
| Qwen 3.5 9B Alibaba Qwen | Q8_0 | fits | 10.0 GB | 39k65k with q8 cache | 23tok/sest. | 1761 tok/s | chat, coding |
| Qwen3 14B Alibaba Qwen | Q4_K_M | fits | 10.5 GB | 12k22k with q8 cache | 22tok/sest. | 1063 tok/s | chat |
| Ministral 3 14B Mistral AI | Q5_K_M | fits | 11.1 GB | 8k16k with q8 cache | 21tok/sest. | 1143 tok/s | chat |
| DeepSeek R1 0528 Qwen3 8B DeepSeek | Q8_0 | fits | 10.1 GB | 15k28k with q8 cache | 23tok/sest. | 1859 tok/s | chat |
| Qwen3 8B Alibaba Qwen | Q8_0 | fits | 10.1 GB | 15k28k with q8 cache | 23tok/sest. | 1859 tok/s | chat |
| Phi-4 14B Microsoft | Q4_K_M | fits | 10.7 GB | 10k16k with q8 cache | 22tok/sest. | 1070 tok/s | chat |
| Qwen 3.5 4B Alibaba Qwen | Q8_0 | fits | 5.3 GB | 166k256k with q8 cache | 48tok/sest. | 3546 tok/s | chat, coding, long documents |
| Ministral 3 8B Mistral AI | Q8_0 | fits | 10.3 GB | 14k26k with q8 cache | 22tok/sest. | 1737 tok/s | chat |
| Granite 4.2 8B IBM | Q8_0 | fits | 10.8 GB | 10k19k with q8 cache | 21tok/sest. | 1724 tok/s | chat |
| Gemma 4 E4B | Q8_0 | fits | 8.7 GB | 82k128k with q8 cache | 27tok/sest. | 2135 tok/s | chat, coding |
| LFM2.5 8B-A1B Liquid AI | Q8_0 | fits | 9.6 GB | 38k65k with q8 cache | 86tok/sest. | 12459 tok/s | chat, coding |
| Llama 3.1 8B Meta | Q6_K | fits | 8.0 GB | 32k58k with q8 cache | 30tok/sest. | 1920 tok/s | chat, coding |
| Qwen2.5 0.5B Alibaba Qwen | Q8_0 | fits | 1.4 GB | 32k | 361tok/sest. | 26075 tok/s | chat, coding, long documents |
| Qwen3.5 0.8B Alibaba Qwen | Q8_0 | fits | 1.7 GB | 256k | 245tok/sest. | 17940 tok/s | chat, coding, agents, long documents |
| Qwen3.5 2B Alibaba Qwen | Q5_K_M | fits | 2.3 GB | 256k | 147tok/sest. | 7359 tok/s | chat, coding, agents, long documents |
| DeepSeek R1 Distill Qwen 1.5B DeepSeek | Q8_0 | fits | 2.8 GB | 128k | 107tok/sest. | 8207 tok/s | chat, coding, long documents |
| MiniCPM5 2B openbmb | Q8_0 | fits | 3.7 GB | 128k | 75tok/sest. | 5425 tok/s | chat, coding, agents, long documents |
| LFM2.5 2.6B Liquid AI | Q8_0 | fits | 4.0 GB | 119k128k with q8 cache | 68tok/sest. | 5460 tok/s | chat, coding, agents, long documents |
| LFM2.5 VL 3B Liquid AI | Q8_0 | fits | 4.0 GB | 32k | 68tok/sest. | 4818 tok/s | chat, coding, agents, long documents |
| granite vision 4.1 4b IBM | Q8_0 | fits | 4.8 GB | 83k128k with q8 cache | 53tok/sest. | 3614 tok/s | chat, coding |
| granite 4.2 3b IBM | Q8_0 | fits | 5.1 GB | 80k128k with q8 cache | 50tok/sest. | 3885 tok/s | chat, coding, agents |
| DeepSeek R1 Distill Qwen 7B DeepSeek | Q8_0 | fits | 8.8 GB | 47k81k with q8 cache | 27tok/sest. | 2071 tok/s | chat, coding |
| DeepSeek R1 Distill Llama 8B DeepSeek | Q8_0 | fits | 9.8 GB | 18k33k with q8 cache | 24tok/sest. | 1920 tok/s | chat |
| Ministral 3 8B Reasoning 2512 Mistral AI | Q8_0 | fits | 10.3 GB | 14k26k with q8 cache | 22tok/sest. | 1737 tok/s | chat |
| GLM 4.6V Flash Z.ai | Q8_0 | fits | 10.5 GB | 24k40k with q8 cache | 22tok/sest. | 1502 tok/s | chat |
| DeepSeek R1 Distill Qwen 14B DeepSeek | Q4_K_M | fits | 10.7 GB | 10k19k with q8 cache | 22tok/sest. | 1041 tok/s | chat |
| Qwen 3.8 27B Alibaba Qwen | UD-Q4_K_M | offload | 16.8 GB | – | 6tok/sest. | 482 tok/s | – |
| Qwen 3.6 27B Alibaba Qwen | Q4_K_M | offload | 17.1 GB | – | 6tok/sest. | 477 tok/s | – |
| Gemma 4 31B | Q4_K_M | offload | 19.3 GB | – | 5tok/sest. | 393 tok/s | – |
| Qwen 3.6 35B-A3B Alibaba Qwen | MXFP4 | offload | 21.3 GB | – | 24tok/sest. | 3689 tok/s | chat |
| Qwen 3.5 27B Alibaba Qwen | Q4_K_M | offload | 17.1 GB | – | 6tok/sest. | 479 tok/s | – |
| Gemma 4 26B-A4B | UD-Q4_K_M | offload | 17.0 GB | – | 19tok/sest. | 3134 tok/s | chat |
| Qwen 3.5 35B-A3B Alibaba Qwen | Q4_K_M | offload | 21.6 GB | – | 23tok/sest. | 3666 tok/s | chat |
| GLM 4.7 Flash Z.ai | Q4_K_M | offload | 18.3 GB | – | 16tok/sest. | 2215 tok/s | chat |
| Devstral Small 2 24B Mistral AI | Q4_K_M | offload | 15.4 GB | – | 8tok/sest. | 569 tok/s | – |
| Nemotron 3.5 Lightning 30B-A3B NVIDIA | UD-Q6_K_XL | offload | 33.5 GB | – | 11tok/sest. | 3221 tok/s | – |
| gpt-oss 20B OpenAI | Q4_K_M | offload | 11.9 GB | – | 41tok/sest. | 3655 tok/s | chat, coding |
| Kimi Linear 48B-A3B Moonshot AI | Q4_K_M | offload | 28.9 GB | – | 21tok/sest. | 3093 tok/s | chat |
| Qwen3 Coder 30B-A3B Alibaba Qwen | Q4_K_M | offload | 18.9 GB | – | 20tok/sest. | 2822 tok/s | chat |
| Qwen3 32B Alibaba Qwen | Q4_K_M | offload | 21.3 GB | – | 4tok/sest. | 332 tok/s | – |
| Mistral Small 3.2 24B Mistral AI | Q4_K_M | offload | 15.4 GB | – | 8tok/sest. | 569 tok/s | – |
| Gemma 3 27B | Q4_K_M | offload | 17.3 GB | – | 6tok/sest. | 482 tok/s | – |
| DeepSeek R1 Distill Qwen 32B DeepSeek | Q4_K_M | offload | 21.3 GB | – | 4tok/sest. | 347 tok/s | – |
| Mellum2.1 12B A2.5B Thinking JetBrains | Q6_K | offload | 11.7 GB | – | 44tok/sest. | 5848 tok/s | chat, coding, agents, long documents |
| Kimi VL A3B Moonshot AI | mlx-5bit | offload | 12.1 GB | – | 41tok/sest. | 4817 tok/s | chat, coding |
| LFM2.5 24B A2B Liquid AI | Q4_K_M | offload | 15.8 GB | – | 32tok/sest. | 5340 tok/s | chat |
| GLM 4.1V 9B Thinking Z.ai | mlx-8bit | offload | 12.1 GB | – | 15tok/sest. | 1428 tok/s | – |
| Devstral Small 2507 Mistral AI | Q4_K_M | offload | 15.4 GB | – | 8tok/sest. | 579 tok/s | – |
| Magistral Small 2506 Mistral AI | Q4_K_M | offload | 15.4 GB | – | 8tok/sest. | 579 tok/s | – |
| Magistral Small 2507 Mistral AI | Q4_K_M | offload | 15.4 GB | – | 8tok/sest. | 579 tok/s | – |
| Magistral Small 2509 Mistral AI | Q4_K_M | offload | 15.4 GB | – | 8tok/sest. | 569 tok/s | – |
| granite 4.2 30b IBM | Q4_K_M | offload | 19.6 GB | – | 5tok/sest. | 406 tok/s | – |
| DeepSeek V4 Flash DeepSeek | UD-Q2_K_XL | won't run | 91.7 GB | – | – | – | – |
| GLM 5.3 Flash Z.ai | UD-Q2_K_XL | won't run | 102.3 GB | – | – | – | – |
| Qwen 3.8 Flash Next Alibaba Qwen | UD-Q2_K_XL | won't run | 74.6 GB | – | – | – | – |
| MiniMax M2.7 MiniMax | UD-Q2_K_XL | won't run | 72.9 GB | – | – | – | – |
| Qwen 3.5 122B-A10B Alibaba Qwen | UD-Q2_K_XL | won't run | 40.1 GB | – | – | – | – |
| Nemotron 3 Super 120B-A12B NVIDIA | UD-Q2_K_XL | won't run | 52.0 GB | – | – | – | – |
| Qwen3 Coder Next Alibaba Qwen | Q4_K_M | won't run | 46.3 GB | – | – | – | – |
| gpt-oss 120B OpenAI | Q4_K_M | won't run | 59.6 GB | – | – | – | – |
| Mistral Small 4 119B Mistral AI | UD-Q2_K_XL | won't run | 38.5 GB | – | – | – | – |
| GLM 4.5 Air Z.ai | Q2_K | won't run | 44.5 GB | – | – | – | – |
| Qwen3 Next 80B-A3B Alibaba Qwen | Q4_K_M | won't run | 46.3 GB | – | – | – | – |
| Llama 3.3 70B Meta | Q4_K_M | won't run | 42.9 GB | – | – | – | – |
| DeepSeek R1 DeepSeek | Q4_K_M | won't run | 378.0 GB | – | – | – | – |
| DeepSeek R1 0528 DeepSeek | Q4_K_M | won't run | 378.5 GB | – | – | – | – |
| DeepSeek R1 Distill Llama 70B DeepSeek | Q4_K_M | won't run | 42.9 GB | – | – | – | – |
| DeepSeek V3 0324 DeepSeek | Q4_K_M | won't run | 378.0 GB | – | – | – | – |
| DeepSeek V3.1 DeepSeek | Q4_K_M | won't run | 378.9 GB | – | – | – | – |
| DeepSeek V3.2 DeepSeek | Q4_K_M | won't run | 378.9 GB | – | – | – | – |
| DeepSeek V4 Flash 0731 DeepSeek | MXFP4 | won't run | 147.2 GB | – | – | – | – |
| DeepSeek V4 Flash Vision Exp DeepSeek | MXFP4 | won't run | 155.9 GB | – | – | – | – |
| Devstral 2 123B Instruct 2512 Mistral AI | Q8_0 | won't run | 127.3 GB | – | – | – | – |
| GLM 4.5V Z.ai | Q4_K_M | won't run | 61.5 GB | – | – | – | – |
| GLM 4.6V Z.ai | Q4_K_M | won't run | 67.9 GB | – | – | – | – |
| GLM 4.7 Z.ai | Q4_K_M | won't run | 205.3 GB | – | – | – | – |
| GLM 5.1 Z.ai | MXFP4 | won't run | 421.5 GB | – | – | – | – |
| GLM 5.2 Z.ai | UD-Q4_K_M | won't run | 435.4 GB | – | – | – | – |
| GLM 5.3 Z.ai | Q8_0 | won't run | 747.9 GB | – | – | – | – |
| Kimi K2 Moonshot AI | Q4_K_M | won't run | 579.5 GB | – | – | – | – |
| Kimi K2 Instruct 0905 Moonshot AI | Q4_K_M | won't run | 580.0 GB | – | – | – | – |
| Kimi K2 Thinking Moonshot AI | Q4_K_M | won't run | 580.0 GB | – | – | – | – |
| Kimi K2.5 Moonshot AI | Q4_K_M | won't run | 580.0 GB | – | – | – | – |
| MiniMax M2 MiniMax | Q4_K_M | won't run | 131.6 GB | – | – | – | – |
| MiniMax M2.1 MiniMax | Q4_K_M | won't run | 131.6 GB | – | – | – | – |
| MiniMax M2.5 MiniMax | MXFP4 | won't run | 118.1 GB | – | – | – | – |
| MiniMax M3 MiniMax | UD-Q4_K_M | won't run | 248.5 GB | – | – | – | – |
| Mistral Medium 3.5 128B Mistral AI | Q4_K_M | won't run | 73.4 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
Compare with
Questions
- How much memory does the Intel Arc B580 have for AI models?
- The Intel Arc B580 has 12 GB of GDDR6 memory with 456 GB/s of bandwidth, which sets how fast it generates text.
- What is the best model the Intel Arc B580 can run locally?
- Gemma 4 12B (Q6_K) fits fully in its memory at 8k context and generates at about 22 tok/s, an estimate from its memory bandwidth. 27 of the 113 models we track fit at that context.
- Can the Intel Arc B580 run DeepSeek V4 Flash?
- No: even at UD-Q2_K_XL, DeepSeek V4 Flash needs about 92 GB at 8k context, more than the Intel Arc B580 and system RAM can hold.
- How much does the Intel Arc B580 cost in Germany?
- The best new price for the Intel Arc B580 in Germany is 360 € at Amazon; used, it starts at 330 € (asking price).
Speeds on this page are for 8k context. See the best hardware for local AI at every budget.