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 128k context it runs 21 of the 113 open models we track fully in memory; the most capable is Gemma 4 26B-A4B at Q4_K_M, at about 23 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 @128k | Prefill | Good for |
|---|---|---|---|---|---|---|---|
| Gemma 4 26B-A4B | Q4_K_M | fits | 20.6 GB | 198k256k with q8 cache | 23tok/sest. | 2535 tok/s | chat, coding, agents, long documents |
| gpt-oss 20B OpenAI | MXFP4 | fits | 16.3 GB | 128k | 22tok/sest. | 1641 tok/s | chat, coding, agents, long documents |
| Gemma 4 12B | Q8_0 | fits | 16.2 GB | 256k | 15tok/sest. | 1053 tok/s | chat, long documents |
| Qwen 3.5 9B Alibaba Qwen | Q8_0 | fits | 15.0 GB | 256k | 16tok/sest. | 1253 tok/s | chat, coding, long documents |
| Qwen 3.5 4B Alibaba Qwen | Q8_0 | fits | 10.3 GB | 256k | 26tok/sest. | 1952 tok/s | chat, coding, long documents |
| Gemma 4 E4B | Q8_0 | fits | 13.2 GB | 128k | 19tok/sest. | 1757 tok/s | chat, coding, long documents |
| LFM2.5 8B-A1B Liquid AI | Q8_0 | fits | 16.4 GB | 125k | 17tok/sest. | 2348 tok/s | chat, coding, long documents |
| Qwen2.5 0.5B Alibaba Qwen | Q8_0 | fits | 4.0 GB | 32k | 107tok/sest. | 5275 tok/s | chat, coding, long documents |
| Qwen3.5 0.8B Alibaba Qwen | Q8_0 | fits | 4.3 GB | 256k | 93tok/sest. | 7035 tok/s | chat, coding, agents, long documents |
| Qwen3.5 2B Alibaba Qwen | Q5_K_M | fits | 4.9 GB | 256k | 74tok/sest. | 4498 tok/s | chat, coding, agents, long documents |
| DeepSeek R1 Distill Qwen 1.5B DeepSeek | Q8_0 | fits | 7.3 GB | 128k | 40tok/sest. | 2357 tok/s | chat, coding, long documents |
| Mellum2.1 12B A2.5B Thinking JetBrains | Q8_0 | fits | 15.9 GB | 128k | 27tok/sest. | 2716 tok/s | chat, coding, agents, long documents |
| MiniCPM5 2B openbmb | Q8_0 | fits | 9.8 GB | 128k | 27tok/sest. | 1267 tok/s | chat, coding, agents, long documents |
| LFM2.5 2.6B Liquid AI | Q8_0 | fits | 12.2 GB | 128k | 21tok/sest. | 1626 tok/s | chat, coding, agents, long documents |
| LFM2.5 VL 3B Liquid AI | Q8_0 | fits | 12.2 GB | 32k | 21tok/sest. | 1564 tok/s | chat, coding, agents, long documents |
| Kimi VL A3B Moonshot AI | mlx-6bit | fits | 18.7 GB | 128k | 19tok/sest. | 1705 tok/s | chat, coding, agents, long documents |
| granite vision 4.1 4b IBM | Q8_0 | fits | 15.4 GB | 128k | 16tok/sest. | 1003 tok/s | chat, coding, long documents |
| granite 4.2 3b IBM | Q8_0 | fits | 15.7 GB | 128k | 16tok/sest. | 1023 tok/s | chat, coding, agents, long documents |
| GLM 4.6V Flash Z.ai | Q8_0 | fits | 16.4 GB | 128k | 15tok/sest. | 550 tok/s | chat, coding |
| DeepSeek R1 Distill Qwen 7B DeepSeek | Q8_0 | fits | 16.6 GB | 128k | 15tok/sest. | 841 tok/s | chat, coding |
| GLM 4.1V 9B Thinking Z.ai | mlx-8bit | fits | 18.0 GB | 64k | 13tok/sest. | 550 tok/s | chat |
| Qwen 3.8 27B Alibaba Qwen | UD-Q4_K_M | offload | 25.5 GB | 82k144k with q8 cache | 6tok/sest. | 395 tok/s | – |
| Qwen 3.5 122B-A10B Alibaba Qwen | UD-Q2_K_XL | offload | 44.2 GB | – | 7tok/sest. | 527 tok/s | – |
| Qwen 3.6 27B Alibaba Qwen | Q4_K_M | offload | 25.9 GB | 77k135k with q8 cache | 6tok/sest. | 392 tok/s | – |
| Gemma 4 31B | Q4_K_M | offload | 29.9 GB | 38k76k with q8 cache | 4tok/sest. | 342 tok/s | – |
| Mistral Small 4 119B Mistral AI | UD-Q2_K_XL | offload | 42.3 GB | – | 9tok/sest. | 466 tok/s | chat |
| Qwen 3.6 35B-A3B Alibaba Qwen | MXFP4 | offload | 24.8 GB | 32k50k with q8 cache | 21tok/sest. | 1955 tok/s | chat, coding, agents, long documents |
| Qwen 3.5 27B Alibaba Qwen | Q4_K_M | offload | 25.8 GB | 78k137k with q8 cache | 6tok/sest. | 393 tok/s | – |
| Qwen 3.5 35B-A3B Alibaba Qwen | Q4_K_M | offload | 25.1 GB | 21k33k with q8 cache | 20tok/sest. | 1941 tok/s | chat, coding, agents, long documents |
| GLM 4.7 Flash Z.ai | Q4_K_M | offload | 25.7 GB | 70k121k with q8 cache | 9tok/sest. | 902 tok/s | chat, coding |
| Devstral Small 2 24B Mistral AI | Q4_K_M | offload | 35.4 GB | 47k87k with q8 cache | 3tok/sest. | 294 tok/s | – |
| Nemotron 3.5 Lightning 30B-A3B NVIDIA | UD-Q6_K_XL | offload | 35.4 GB | – | 13tok/sest. | 2151 tok/s | chat |
| Kimi Linear 48B-A3B Moonshot AI | Q4_K_M | offload | 31.1 GB | – | 22tok/sest. | 1286 tok/s | chat, coding, long documents |
| Qwen3 Coder 30B-A3B Alibaba Qwen | Q4_K_M | offload | 31.3 GB | 38k68k with q8 cache | 4tok/sest. | 496 tok/s | chat, coding |
| Gemma 3 27B | Q4_K_M | offload | 27.9 GB | 62k115k with q8 cache | 5tok/sest. | 459 tok/s | – |
| Mistral Small 3.2 24B Mistral AI | Q4_K_M | offload | 35.4 GB | 47k87k with q8 cache | 3tok/sest. | 294 tok/s | – |
| Ministral 3 14B Mistral AI | Q4_K_M | offload | 29.7 GB | 82k151k with q8 cache | 4tok/sest. | 415 tok/s | chat |
| Qwen3 14B Alibaba Qwen | Q4_K_M | offload | 30.4 GB | 40k | 4tok/sest. | 349 tok/s | chat |
| DeepSeek R1 0528 Qwen3 8B DeepSeek | Q4_K_M | offload | 24.7 GB | 112k128k with q8 cache | 7tok/sest. | 596 tok/s | chat, coding |
| Qwen3 8B Alibaba Qwen | Q4_K_M | offload | 24.7 GB | 40k | 7tok/sest. | 596 tok/s | chat, coding |
| Phi-4 14B Microsoft | Q4_K_M | offload | 35.3 GB | 16k | 3tok/sest. | 323 tok/s | chat |
| Ministral 3 8B Mistral AI | Q4_K_M | offload | 23.9 GB | 117k212k with q8 cache | 8tok/sest. | 617 tok/s | chat, coding |
| Granite 4.2 8B IBM | Q4_K_M | offload | 27.2 GB | 98k128k with q8 cache | 5tok/sest. | 511 tok/s | chat, coding |
| Llama 3.1 8B Meta | Q4_K_M | offload | 22.6 GB | 126k128k with q8 cache | 10tok/sest. | 689 tok/s | chat, coding |
| DeepSeek R1 Distill Llama 8B DeepSeek | Q4_K_M | offload | 22.6 GB | 126k128k with q8 cache | 10tok/sest. | 689 tok/s | chat, coding |
| Ministral 3 8B Reasoning 2512 Mistral AI | Q4_K_M | offload | 23.9 GB | 117k212k with q8 cache | 8tok/sest. | 617 tok/s | chat, coding |
| LFM2.5 24B A2B Liquid AI | Q4_K_M | offload | 26.3 GB | 80k128k with q8 cache | 7tok/sest. | 1238 tok/s | chat, coding, agents |
| DeepSeek R1 Distill Qwen 14B DeepSeek | Q4_K_M | offload | 34.4 GB | 65k120k with q8 cache | 3tok/sest. | 289 tok/s | chat |
| Devstral Small 2507 Mistral AI | Q4_K_M | offload | 35.4 GB | 47k87k with q8 cache | 3tok/sest. | 297 tok/s | – |
| Magistral Small 2506 Mistral AI | Q4_K_M | offload | 35.4 GB | 40k | 3tok/sest. | 297 tok/s | – |
| Magistral Small 2507 Mistral AI | Q4_K_M | offload | 35.4 GB | 40k | 3tok/sest. | 297 tok/s | – |
| Magistral Small 2509 Mistral AI | Q4_K_M | offload | 35.4 GB | 47k87k with q8 cache | 3tok/sest. | 294 tok/s | – |
| DeepSeek V4 Flash DeepSeek | UD-Q2_K_XL | won't run | 103.0 GB | – | – | – | – |
| GLM 5.3 Flash Z.ai | UD-Q2_K_XL | won't run | 104.8 GB | – | – | – | – |
| Qwen 3.8 Flash Next Alibaba Qwen | UD-Q2_K_XL | won't run | 78.6 GB | – | – | – | – |
| MiniMax M2.7 MiniMax | UD-Q2_K_XL | won't run | 103.2 GB | – | – | – | – |
| Nemotron 3 Super 120B-A12B NVIDIA | UD-Q2_K_XL | won't run | 54.1 GB | – | – | – | – |
| Qwen3 Coder Next Alibaba Qwen | Q4_K_M | won't run | 50.3 GB | – | – | – | – |
| gpt-oss 120B OpenAI | Q4_K_M | won't run | 65.0 GB | – | – | – | – |
| GLM 4.5 Air Z.ai | Q2_K | won't run | 67.3 GB | – | – | – | – |
| Qwen3 Next 80B-A3B Alibaba Qwen | Q4_K_M | won't run | 50.3 GB | – | – | – | – |
| Qwen3 32B Alibaba Qwen | Q4_K_M | won't run | 52.5 GB | 10k19k with q8 cache | – | – | – |
| DeepSeek R1 Distill Qwen 32B DeepSeek | Q4_K_M | won't run | 52.5 GB | 10k18k with q8 cache | – | – | – |
| Llama 3.3 70B Meta | Q4_K_M | won't run | 81.7 GB | – | – | – | – |
| DeepSeek R1 DeepSeek | Q4_K_M | won't run | 387.3 GB | – | – | – | – |
| DeepSeek R1 0528 DeepSeek | Q4_K_M | won't run | 387.8 GB | – | – | – | – |
| DeepSeek R1 Distill Llama 70B DeepSeek | Q4_K_M | won't run | 81.7 GB | – | – | – | – |
| DeepSeek V3 0324 DeepSeek | Q4_K_M | won't run | 387.3 GB | – | – | – | – |
| DeepSeek V3.1 DeepSeek | Q4_K_M | won't run | 388.2 GB | – | – | – | – |
| DeepSeek V3.2 DeepSeek | Q4_K_M | won't run | 388.2 GB | – | – | – | – |
| DeepSeek V4 Flash 0731 DeepSeek | MXFP4 | won't run | 158.4 GB | – | – | – | – |
| DeepSeek V4 Flash Vision Exp DeepSeek | MXFP4 | won't run | 167.2 GB | – | – | – | – |
| Devstral 2 123B Instruct 2512 Mistral AI | Q8_0 | won't run | 169.8 GB | – | – | – | – |
| GLM 4.5V Z.ai | Q4_K_M | won't run | 84.3 GB | – | – | – | – |
| GLM 4.6V Z.ai | Q4_K_M | won't run | 90.7 GB | – | – | – | – |
| GLM 4.7 Z.ai | Q4_K_M | won't run | 249.6 GB | – | – | – | – |
| GLM 5.1 Z.ai | MXFP4 | won't run | 433.0 GB | – | – | – | – |
| GLM 5.2 Z.ai | UD-Q4_K_M | won't run | 446.9 GB | – | – | – | – |
| GLM 5.3 Z.ai | Q8_0 | won't run | 759.3 GB | – | – | – | – |
| Kimi K2 Moonshot AI | Q4_K_M | won't run | 588.8 GB | – | – | – | – |
| Kimi K2 Instruct 0905 Moonshot AI | Q4_K_M | won't run | 589.2 GB | – | – | – | – |
| Kimi K2 Thinking Moonshot AI | Q4_K_M | won't run | 589.2 GB | – | – | – | – |
| Kimi K2.5 Moonshot AI | Q4_K_M | won't run | 589.2 GB | – | – | – | – |
| MiniMax M2 MiniMax | Q4_K_M | won't run | 161.9 GB | – | – | – | – |
| MiniMax M2.1 MiniMax | Q4_K_M | won't run | 161.9 GB | – | – | – | – |
| MiniMax M2.5 MiniMax | MXFP4 | won't run | 148.3 GB | – | – | – | – |
| MiniMax M3 MiniMax | UD-Q4_K_M | won't run | 263.8 GB | – | – | – | – |
| Mistral Medium 3.5 128B Mistral AI | Q4_K_M | won't run | 115.8 GB | – | – | – | – |
| granite 4.2 30b IBM | Q4_K_M | won't run | 50.8 GB | 16k31k with q8 cache | – | – | – |
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 26B-A4B (Q4_K_M) fits fully in its memory at 128k context and generates at about 23 tok/s, an estimate from its memory bandwidth. 21 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 103 GB at 128k 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 128k context. See the best hardware for local AI at every budget.