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 64k context it runs 36 of the 113 open models we track fully in memory; the most capable is Qwen 3.8 27B at Q4_K_M, at about 10 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 | 3 h ago | Buy |
| eBayASRock Intel Arc B580 Steel Legend Gaming OC Grafikkarte 12GB GDDR6 weiß | used, asking price | 350 €+ 6 € delivery | In stock | 3 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 | 3 h ago | Buy |
| AmazonSparkle Technology Intel Arc B580 Titan Oc 12 GB Gddr6 | New | 405 € | In stock | 1 h ago | Buy |
| eBaySparkle Intel Arc B580 TITAN OC SB580T-12GOC 12GB GDDR6 1x HDMI 3x DP | New | 500 €+ 9 € delivery | In stock | 3 h ago | Buy |
| eBaySparkle Arc B580 Guardian | New | 621 €+ 18 € delivery | In stock | 3 h ago | Buy |
Price history
Lowest price shown each day over the last 90 days.
Not enough price history yet.
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 | Q4_K_M | fits | 22.1 GB | 68k120k with q8 cache | 10tok/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 | Q5_K_M | fits | 21.1 GB | 114k185k with q8 cache | 28tok/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 |
| Qwen2.5 0.5B Alibaba Qwen | Q8_0 | fits | 2.9 GB | 32k | 171tok/sest. | 9181 tok/s | chat, coding, long documents |
| Qwen3.5 0.8B Alibaba Qwen | Q8_0 | fits | 3.2 GB | 256k | 139tok/sest. | 10410 tok/s | chat, coding, agents, long documents |
| Qwen3.5 2B Alibaba Qwen | Q5_K_M | fits | 3.8 GB | 256k | 101tok/sest. | 5675 tok/s | chat, coding, agents, long documents |
| DeepSeek R1 Distill Qwen 1.5B DeepSeek | Q8_0 | fits | 5.2 GB | 128k | 60tok/sest. | 3803 tok/s | chat, coding, long documents |
| MiniCPM5 2B openbmb | Q8_0 | fits | 6.8 GB | 128k | 42tok/sest. | 2143 tok/s | chat, coding, agents, long documents |
| Mellum2.1 12B A2.5B Thinking JetBrains | Q8_0 | fits | 14.6 GB | 128k | 34tok/sest. | 3836 tok/s | chat, coding, agents, long documents |
| LFM2.5 2.6B Liquid AI | Q8_0 | fits | 8.1 GB | 128k | 33tok/sest. | 2599 tok/s | chat, coding, agents, long documents |
| LFM2.5 VL 3B Liquid AI | Q8_0 | fits | 8.1 GB | 32k | 33tok/sest. | 2444 tok/s | chat, coding, agents, long documents |
| granite vision 4.1 4b IBM | Q8_0 | fits | 10.0 GB | 128k | 25tok/sest. | 1632 tok/s | chat, coding, long documents |
| granite 4.2 3b IBM | Q8_0 | fits | 10.3 GB | 128k | 25tok/sest. | 1685 tok/s | chat, coding, agents, long documents |
| Kimi VL A3B Moonshot AI | mlx-8bit | fits | 20.2 GB | 126k128k with q8 cache | 24tok/sest. | 2638 tok/s | chat, coding, long documents |
| DeepSeek R1 Distill Qwen 7B DeepSeek | Q8_0 | fits | 12.7 GB | 128k | 19tok/sest. | 1231 tok/s | chat, coding |
| LFM2.5 24B A2B Liquid AI | Q4_K_M | fits | 21.0 GB | 80k128k with q8 cache | 19tok/sest. | 2372 tok/s | chat, coding, agents |
| GLM 4.6V Flash Z.ai | Q8_0 | fits | 13.5 GB | 128k | 18tok/sest. | 831 tok/s | chat, coding |
| GLM 4.1V 9B Thinking Z.ai | mlx-8bit | fits | 15.1 GB | 64k | 16tok/sest. | 831 tok/s | chat |
| DeepSeek R1 Distill Llama 8B DeepSeek | Q8_0 | fits | 17.6 GB | 100k128k with q8 cache | 13tok/sest. | 1051 tok/s | chat |
| Ministral 3 8B Reasoning 2512 Mistral AI | Q8_0 | fits | 18.6 GB | 91k166k with q8 cache | 13tok/sest. | 968 tok/s | chat |
| DeepSeek R1 Distill Qwen 14B DeepSeek | Q4_K_M | fits | 22.0 GB | 65k120k with q8 cache | 10tok/sest. | 566 tok/s | chat |
| 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 | MXFP4 | offload | 23.2 GB | 32k50k with q8 cache | 35tok/sest. | 3006 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 |
| Devstral Small 2507 Mistral AI | Q4_K_M | offload | 25.0 GB | 47k87k with q8 cache | 7tok/sest. | 475 tok/s | – |
| Magistral Small 2506 Mistral AI | Q4_K_M | offload | 25.0 GB | 40k | 7tok/sest. | 475 tok/s | – |
| Magistral Small 2507 Mistral AI | Q4_K_M | offload | 25.0 GB | 40k | 7tok/sest. | 475 tok/s | – |
| Magistral Small 2509 Mistral AI | Q4_K_M | offload | 25.0 GB | 47k87k with q8 cache | 7tok/sest. | 469 tok/s | – |
| granite 4.2 30b IBM | Q4_K_M | offload | 34.5 GB | 16k31k with q8 cache | 3tok/sest. | 293 tok/s | – |
| 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 | Q4_K_M | won't run | 62.4 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 | – | – | – | – |
| DeepSeek R1 DeepSeek | Q4_K_M | won't run | 382.6 GB | – | – | – | – |
| DeepSeek R1 0528 DeepSeek | Q4_K_M | won't run | 383.1 GB | – | – | – | – |
| DeepSeek R1 Distill Llama 70B DeepSeek | Q4_K_M | won't run | 61.3 GB | – | – | – | – |
| DeepSeek V3 0324 DeepSeek | Q4_K_M | won't run | 382.6 GB | – | – | – | – |
| DeepSeek V3.1 DeepSeek | Q4_K_M | won't run | 383.5 GB | – | – | – | – |
| DeepSeek V3.2 DeepSeek | Q4_K_M | won't run | 383.5 GB | – | – | – | – |
| DeepSeek V4 Flash 0731 DeepSeek | MXFP4 | won't run | 152.7 GB | – | – | – | – |
| DeepSeek V4 Flash Vision Exp DeepSeek | MXFP4 | won't run | 161.5 GB | – | – | – | – |
| Devstral 2 123B Instruct 2512 Mistral AI | Q8_0 | won't run | 147.4 GB | – | – | – | – |
| GLM 4.5V Z.ai | Q4_K_M | won't run | 72.4 GB | – | – | – | – |
| GLM 4.6V Z.ai | Q4_K_M | won't run | 78.8 GB | – | – | – | – |
| GLM 4.7 Z.ai | Q4_K_M | won't run | 226.3 GB | – | – | – | – |
| GLM 5.1 Z.ai | MXFP4 | won't run | 427.1 GB | – | – | – | – |
| GLM 5.2 Z.ai | UD-Q4_K_M | won't run | 441.0 GB | – | – | – | – |
| GLM 5.3 Z.ai | Q8_0 | won't run | 753.5 GB | – | – | – | – |
| Kimi K2 Moonshot AI | Q4_K_M | won't run | 584.1 GB | – | – | – | – |
| Kimi K2 Instruct 0905 Moonshot AI | Q4_K_M | won't run | 584.5 GB | – | – | – | – |
| Kimi K2 Thinking Moonshot AI | Q4_K_M | won't run | 584.5 GB | – | – | – | – |
| Kimi K2.5 Moonshot AI | Q4_K_M | won't run | 584.5 GB | – | – | – | – |
| MiniMax M2 MiniMax | Q4_K_M | won't run | 146.0 GB | – | – | – | – |
| MiniMax M2.1 MiniMax | Q4_K_M | won't run | 146.0 GB | – | – | – | – |
| MiniMax M2.5 MiniMax | MXFP4 | won't run | 132.4 GB | – | – | – | – |
| MiniMax M3 MiniMax | UD-Q4_K_M | won't run | 255.9 GB | – | – | – | – |
| Mistral Medium 3.5 128B Mistral AI | Q4_K_M | won't run | 93.4 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?
- Qwen 3.8 27B (Q4_K_M) fits fully in its memory at 64k context and generates at about 10 tok/s, an estimate from its memory bandwidth. 36 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 97 GB at 64k 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 64k context. See the best hardware for local AI at every budget.