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 51 of the 113 open models we track fully in memory; the most capable is Qwen 3.8 27B at Q5_K_M, at about 11 tok/s (estimated). The best new price for the Intel Arc B580 in Canada is $550 at eBay; used, it starts at $450 (asking price).
Updated . Speeds are estimates; how they are worked out.
Prices
Every retailer we track in Canada, cheapest first. Buy links may earn us a commission.
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 @8k | Prefill | Good for |
|---|---|---|---|---|---|---|---|
| Qwen 3.8 27B Alibaba Qwen | Q5_K_M | fits | 21.5 GB | 21k37k 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 | Q4_K_M | fits | 22.3 GB | 11k17k 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 |
| Qwen2.5 0.5B Alibaba Qwen | Q8_0 | fits | 1.9 GB | 32k | 361tok/sest. | 26075 tok/s | chat, coding, long documents |
| Qwen3.5 0.8B Alibaba Qwen | Q8_0 | fits | 2.2 GB | 256k | 245tok/sest. | 17940 tok/s | chat, coding, agents, long documents |
| Qwen3.5 2B Alibaba Qwen | Q5_K_M | fits | 2.8 GB | 256k | 147tok/sest. | 7359 tok/s | chat, coding, agents, long documents |
| DeepSeek R1 Distill Qwen 1.5B DeepSeek | Q8_0 | fits | 3.3 GB | 128k | 107tok/sest. | 8207 tok/s | chat, coding, long documents |
| MiniCPM5 2B openbmb | Q8_0 | fits | 4.2 GB | 128k | 75tok/sest. | 5425 tok/s | chat, coding, agents, long documents |
| LFM2.5 2.6B Liquid AI | Q8_0 | fits | 4.5 GB | 128k | 68tok/sest. | 5460 tok/s | chat, coding, agents, long documents |
| LFM2.5 VL 3B Liquid AI | Q8_0 | fits | 4.5 GB | 32k | 68tok/sest. | 4818 tok/s | chat, coding, agents, long documents |
| granite vision 4.1 4b IBM | Q8_0 | fits | 5.3 GB | 128k | 53tok/sest. | 3614 tok/s | chat, coding, long documents |
| LFM2.5 24B A2B Liquid AI | Q6_K | fits | 21.7 GB | 16k29k with q8 cache | 52tok/sest. | 6542 tok/s | chat, coding |
| granite 4.2 3b IBM | Q8_0 | fits | 5.6 GB | 128k | 50tok/sest. | 3885 tok/s | chat, coding, agents, long documents |
| Mellum2.1 12B A2.5B Thinking JetBrains | Q8_0 | fits | 13.5 GB | 128k | 45tok/sest. | 6003 tok/s | chat, coding, agents, long documents |
| Kimi VL A3B Moonshot AI | mlx-8bit | fits | 18.2 GB | 126k128k with q8 cache | 36tok/sest. | 5061 tok/s | chat, coding, long documents |
| DeepSeek R1 Distill Qwen 7B DeepSeek | Q8_0 | fits | 9.3 GB | 128k | 27tok/sest. | 2071 tok/s | chat, coding |
| DeepSeek R1 Distill Llama 8B DeepSeek | Q8_0 | fits | 10.3 GB | 100k128k with q8 cache | 24tok/sest. | 1920 tok/s | chat |
| Ministral 3 8B Reasoning 2512 Mistral AI | Q8_0 | fits | 10.8 GB | 91k166k with q8 cache | 22tok/sest. | 1737 tok/s | chat |
| GLM 4.6V Flash Z.ai | Q8_0 | fits | 11.0 GB | 128k | 22tok/sest. | 1502 tok/s | chat, coding |
| GLM 4.1V 9B Thinking Z.ai | mlx-8bit | fits | 12.6 GB | 64k | 19tok/sest. | 1502 tok/s | chat |
| DeepSeek R1 Distill Qwen 14B DeepSeek | Q8_0 | fits | 17.5 GB | 33k61k with q8 cache | 13tok/sest. | 1041 tok/s | – |
| Devstral Small 2507 Mistral AI | Q5_K_M | fits | 18.2 GB | 33k61k with q8 cache | 13tok/sest. | 701 tok/s | – |
| Magistral Small 2507 Mistral AI | Q5_K_M | fits | 18.2 GB | 33k40k with q8 cache | 13tok/sest. | 701 tok/s | – |
| Magistral Small 2509 Mistral AI | Q5_K_M | fits | 18.2 GB | 33k61k with q8 cache | 13tok/sest. | 689 tok/s | – |
| granite 4.2 30b IBM | Q4_K_M | fits | 20.1 GB | 16k31k with q8 cache | 11tok/sest. | 556 tok/s | – |
| Magistral Small 2506 Mistral AI | Q6_K | fits | 20.6 GB | 19k34k with q8 cache | 11tok/sest. | 701 tok/s | – |
| 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 R1 Distill Llama 70B DeepSeek | 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 | Q4_K_M | won't run | 60.1 GB | – | – | – | – |
| DeepSeek R1 DeepSeek | Q4_K_M | won't run | 378.5 GB | – | – | – | – |
| DeepSeek R1 0528 DeepSeek | Q4_K_M | won't run | 379.0 GB | – | – | – | – |
| DeepSeek V3 0324 DeepSeek | Q4_K_M | won't run | 378.5 GB | – | – | – | – |
| DeepSeek V3.1 DeepSeek | Q4_K_M | won't run | 379.4 GB | – | – | – | – |
| DeepSeek V3.2 DeepSeek | Q4_K_M | won't run | 379.4 GB | – | – | – | – |
| DeepSeek V4 Flash 0731 DeepSeek | MXFP4 | won't run | 147.7 GB | – | – | – | – |
| DeepSeek V4 Flash Vision Exp DeepSeek | MXFP4 | won't run | 156.4 GB | – | – | – | – |
| Devstral 2 123B Instruct 2512 Mistral AI | Q8_0 | won't run | 127.8 GB | – | – | – | – |
| GLM 4.5V Z.ai | Q4_K_M | won't run | 62.0 GB | – | – | – | – |
| GLM 4.6V Z.ai | Q4_K_M | won't run | 68.4 GB | – | – | – | – |
| GLM 4.7 Z.ai | Q4_K_M | won't run | 205.8 GB | – | – | – | – |
| GLM 5.1 Z.ai | MXFP4 | won't run | 422.0 GB | – | – | – | – |
| GLM 5.2 Z.ai | UD-Q4_K_M | won't run | 435.9 GB | – | – | – | – |
| GLM 5.3 Z.ai | Q8_0 | won't run | 748.4 GB | – | – | – | – |
| Kimi K2 Moonshot AI | Q4_K_M | won't run | 580.0 GB | – | – | – | – |
| Kimi K2 Instruct 0905 Moonshot AI | Q4_K_M | won't run | 580.5 GB | – | – | – | – |
| Kimi K2 Thinking Moonshot AI | Q4_K_M | won't run | 580.5 GB | – | – | – | – |
| Kimi K2.5 Moonshot AI | Q4_K_M | won't run | 580.5 GB | – | – | – | – |
| MiniMax M2 MiniMax | Q4_K_M | won't run | 132.1 GB | – | – | – | – |
| MiniMax M2.1 MiniMax | Q4_K_M | won't run | 132.1 GB | – | – | – | – |
| MiniMax M2.5 MiniMax | MXFP4 | won't run | 118.6 GB | – | – | – | – |
| MiniMax M3 MiniMax | UD-Q4_K_M | won't run | 249.0 GB | – | – | – | – |
| Mistral Medium 3.5 128B Mistral AI | Q4_K_M | won't run | 73.9 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 (Q5_K_M) fits fully in its memory at 8k context and generates at about 11 tok/s, an estimate from its memory bandwidth. 51 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 Canada?
- The best new price for the Intel Arc B580 in Canada is $550 at eBay; used, it starts at $450 (asking price).
Speeds on this page are for 8k context. See the best hardware for local AI at every budget.