Intel Arc Pro B60
24 GB · 456 GB/s · 200 W
In short
The Intel Arc Pro B60 has 24 GB of GDDR6 memory with 456 GB/s of bandwidth, which sets how fast it generates text. At 64k context it runs 40 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 Pro B60 in Canada is $985 at Amazon.
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.
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 |
|---|---|---|---|---|---|---|---|
| Qwen 3.8 27B Alibaba Qwen | Q4_K_M | fits | 21.6 GB | 87k153k with q8 cache | 10tok/sest. | 432 tok/s | – |
| Qwen 3.6 27B Alibaba Qwen | Q4_K_M | fits | 21.0 GB | 96k168k with q8 cache | 11tok/sest. | 432 tok/s | – |
| Qwen 3.6 35B-A3B Alibaba Qwen | UD-Q4_K_M | fits | 23.1 GB | 68k106k with q8 cache | 39tok/sest. | 2599 tok/s | chat, coding, agents, long documents |
| Qwen 3.5 27B Alibaba Qwen | Q4_K_M | fits | 20.9 GB | 97k170k with q8 cache | 11tok/sest. | 432 tok/s | – |
| Gemma 4 26B-A4B | UD-Q5_K_M | fits | 22.3 GB | 98k160k with q8 cache | 26tok/sest. | 2661 tok/s | chat, coding, agents, long documents |
| Qwen 3.5 35B-A3B Alibaba Qwen | Q4_K_M | fits | 23.0 GB | 72k113k with q8 cache | 39tok/sest. | 2599 tok/s | chat, coding, agents, long documents |
| GLM 4.7 Flash Z.ai | Q4_K_M | fits | 21.5 GB | 92k160k with q8 cache | 19tok/sest. | 1289 tok/s | chat, coding |
| gpt-oss 20B OpenAI | MXFP4 | fits | 14.0 GB | 128k | 31tok/sest. | 1989 tok/s | chat, coding, agents, long documents |
| Gemma 4 12B | Q8_0 | fits | 14.3 GB | 256k | 16tok/sest. | 1023 tok/s | chat, long documents |
| Qwen 3.5 9B Alibaba Qwen | Q8_0 | fits | 12.1 GB | 256k | 19tok/sest. | 1252 tok/s | chat, coding, long documents |
| Gemma 3 27B | Q4_K_M | fits | 22.0 GB | 78k128k with q8 cache | 10tok/sest. | 484 tok/s | – |
| Ministral 3 14B Mistral AI | Q6_K | fits | 21.5 GB | 74k135k with q8 cache | 10tok/sest. | 599 tok/s | chat |
| Qwen3 14B Alibaba Qwen | Q6_K | fits | 22.5 GB | 40k | 10tok/sest. | 524 tok/s | chat |
| DeepSeek R1 0528 Qwen3 8B DeepSeek | Q8_0 | fits | 18.3 GB | 97k128k with q8 cache | 12tok/sest. | 828 tok/s | chat |
| Qwen3 8B Alibaba Qwen | Q8_0 | fits | 18.3 GB | 40k | 12tok/sest. | 828 tok/s | chat |
| Phi-4 14B Microsoft | Q4_K_M | fits | 22.0 GB | 16k | 10tok/sest. | 526 tok/s | chat |
| Qwen 3.5 4B Alibaba Qwen | Q8_0 | fits | 7.4 GB | 256k | 34tok/sest. | 2170 tok/s | chat, coding, long documents |
| Ministral 3 8B Mistral AI | Q8_0 | fits | 18.1 GB | 100k183k with q8 cache | 13tok/sest. | 819 tok/s | chat |
| Granite 4.2 8B IBM | Q8_0 | fits | 19.9 GB | 84k128k with q8 cache | 11tok/sest. | 757 tok/s | chat |
| Gemma 4 E4B | Q8_0 | fits | 10.6 GB | 128k | 23tok/sest. | 1640 tok/s | chat, coding, long documents |
| LFM2.5 8B-A1B Liquid AI | Q8_0 | fits | 12.6 GB | 125k | 29tok/sest. | 3500 tok/s | chat, coding, long documents |
| Llama 3.1 8B Meta | Q6_K | fits | 15.3 GB | 124k128k with q8 cache | 15tok/sest. | 889 tok/s | chat, coding |
| Qwen2.5 0.5B Alibaba Qwen | Q8_0 | fits | 2.4 GB | 32k | 171tok/sest. | 7763 tok/s | chat, coding, long documents |
| Qwen3.5 0.8B Alibaba Qwen | Q8_0 | fits | 2.7 GB | 256k | 139tok/sest. | 8801 tok/s | chat, coding, agents, long documents |
| Qwen3.5 2B Alibaba Qwen | Q5_K_M | fits | 3.3 GB | 256k | 101tok/sest. | 4798 tok/s | chat, coding, agents, long documents |
| DeepSeek R1 Distill Qwen 1.5B DeepSeek | Q8_0 | fits | 4.7 GB | 128k | 60tok/sest. | 3215 tok/s | chat, coding, long documents |
| MiniCPM5 2B openbmb | Q8_0 | fits | 6.3 GB | 128k | 42tok/sest. | 1812 tok/s | chat, coding, agents, long documents |
| Mellum2.1 12B A2.5B Thinking JetBrains | Q8_0 | fits | 14.1 GB | 128k | 34tok/sest. | 3244 tok/s | chat, coding, agents, long documents |
| LFM2.5 2.6B Liquid AI | Q8_0 | fits | 7.6 GB | 128k | 33tok/sest. | 2197 tok/s | chat, coding, agents, long documents |
| LFM2.5 VL 3B Liquid AI | Q8_0 | fits | 7.6 GB | 32k | 33tok/sest. | 2066 tok/s | chat, coding, agents, long documents |
| granite vision 4.1 4b IBM | Q8_0 | fits | 9.5 GB | 128k | 25tok/sest. | 1380 tok/s | chat, coding, long documents |
| granite 4.2 3b IBM | Q8_0 | fits | 9.8 GB | 128k | 25tok/sest. | 1425 tok/s | chat, coding, agents, long documents |
| Kimi VL A3B Moonshot AI | mlx-8bit | fits | 19.7 GB | 128k | 24tok/sest. | 2231 tok/s | chat, coding, long documents |
| DeepSeek R1 Distill Qwen 7B DeepSeek | Q8_0 | fits | 12.2 GB | 128k | 19tok/sest. | 1041 tok/s | chat, coding |
| LFM2.5 24B A2B Liquid AI | Q4_K_M | fits | 20.5 GB | 96k128k with q8 cache | 19tok/sest. | 2005 tok/s | chat, coding, agents |
| GLM 4.6V Flash Z.ai | Q8_0 | fits | 13.0 GB | 128k | 18tok/sest. | 703 tok/s | chat, coding |
| GLM 4.1V 9B Thinking Z.ai | mlx-8bit | fits | 14.6 GB | 64k | 16tok/sest. | 703 tok/s | chat |
| DeepSeek R1 Distill Llama 8B DeepSeek | Q8_0 | fits | 17.1 GB | 110k128k with q8 cache | 13tok/sest. | 889 tok/s | chat |
| Ministral 3 8B Reasoning 2512 Mistral AI | Q8_0 | fits | 18.1 GB | 100k183k with q8 cache | 13tok/sest. | 819 tok/s | chat |
| DeepSeek R1 Distill Qwen 14B DeepSeek | Q5_K_M | fits | 23.0 GB | 65k119k with q8 cache | 10tok/sest. | 479 tok/s | chat |
| Qwen 3.5 122B-A10B Alibaba Qwen | UD-Q2_K_XL | offload | 41.8 GB | – | 10tok/sest. | 652 tok/s | – |
| Qwen3 Coder Next Alibaba Qwen | Q4_K_M | offload | 47.9 GB | – | 11tok/sest. | 1421 tok/s | chat |
| Gemma 4 31B | Q4_K_M | offload | 24.0 GB | 54k103k with q8 cache | 8tok/sest. | 386 tok/s | – |
| Mistral Small 4 119B Mistral AI | UD-Q2_K_XL | offload | 40.0 GB | – | 13tok/sest. | 654 tok/s | chat |
| Qwen3 Next 80B-A3B Alibaba Qwen | Q4_K_M | offload | 47.9 GB | – | 13tok/sest. | 1621 tok/s | chat |
| Devstral Small 2 24B Mistral AI | Q4_K_M | offload | 24.5 GB | 55k101k with q8 cache | 8tok/sest. | 411 tok/s | – |
| Nemotron 3.5 Lightning 30B-A3B NVIDIA | UD-Q6_K_XL | offload | 34.2 GB | – | 16tok/sest. | 2564 tok/s | chat |
| Kimi Linear 48B-A3B Moonshot AI | Q4_K_M | offload | 29.7 GB | – | 30tok/sest. | 1802 tok/s | chat, coding, long documents |
| Qwen3 Coder 30B-A3B Alibaba Qwen | Q4_K_M | offload | 24.5 GB | 51k91k with q8 cache | 13tok/sest. | 900 tok/s | chat, coding |
| Qwen3 32B Alibaba Qwen | Q4_K_M | offload | 35.6 GB | 15k28k with q8 cache | 3tok/sest. | 173 tok/s | – |
| Mistral Small 3.2 24B Mistral AI | Q4_K_M | offload | 24.5 GB | 55k101k with q8 cache | 8tok/sest. | 411 tok/s | – |
| DeepSeek R1 Distill Qwen 32B DeepSeek | Q4_K_M | offload | 35.7 GB | 15k28k with q8 cache | 3tok/sest. | 213 tok/s | – |
| Devstral Small 2507 Mistral AI | Q4_K_M | offload | 24.5 GB | 55k101k with q8 cache | 8tok/sest. | 416 tok/s | – |
| Magistral Small 2506 Mistral AI | Q4_K_M | offload | 24.5 GB | 40k | 8tok/sest. | 416 tok/s | – |
| Magistral Small 2507 Mistral AI | Q4_K_M | offload | 24.5 GB | 40k | 8tok/sest. | 416 tok/s | – |
| Magistral Small 2509 Mistral AI | Q4_K_M | offload | 24.5 GB | 55k101k with q8 cache | 8tok/sest. | 411 tok/s | – |
| granite 4.2 30b IBM | Q4_K_M | offload | 34.0 GB | 21k40k with q8 cache | 3tok/sest. | 255 tok/s | – |
| 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 | – | – | – | – |
| Nemotron 3 Super 120B-A12B NVIDIA | UD-Q2_K_XL | won't run | 52.7 GB | – | – | – | – |
| gpt-oss 120B OpenAI | Q4_K_M | won't run | 61.9 GB | – | – | – | – |
| GLM 4.5 Air Z.ai | Q2_K | won't run | 54.9 GB | – | – | – | – |
| Llama 3.3 70B Meta | Q4_K_M | won't run | 60.8 GB | – | – | – | – |
| DeepSeek R1 DeepSeek | Q4_K_M | won't run | 382.1 GB | – | – | – | – |
| DeepSeek R1 0528 DeepSeek | Q4_K_M | won't run | 382.6 GB | – | – | – | – |
| DeepSeek R1 Distill Llama 70B DeepSeek | Q4_K_M | won't run | 60.8 GB | – | – | – | – |
| DeepSeek V3 0324 DeepSeek | Q4_K_M | won't run | 382.1 GB | – | – | – | – |
| DeepSeek V3.1 DeepSeek | Q4_K_M | won't run | 383.0 GB | – | – | – | – |
| DeepSeek V3.2 DeepSeek | Q4_K_M | won't run | 383.0 GB | – | – | – | – |
| DeepSeek V4 Flash 0731 DeepSeek | MXFP4 | won't run | 152.2 GB | – | – | – | – |
| DeepSeek V4 Flash Vision Exp DeepSeek | MXFP4 | won't run | 161.0 GB | – | – | – | – |
| Devstral 2 123B Instruct 2512 Mistral AI | Q8_0 | won't run | 146.9 GB | – | – | – | – |
| GLM 4.5V Z.ai | Q4_K_M | won't run | 71.9 GB | – | – | – | – |
| GLM 4.6V Z.ai | Q4_K_M | won't run | 78.3 GB | – | – | – | – |
| GLM 4.7 Z.ai | Q4_K_M | won't run | 225.8 GB | – | – | – | – |
| GLM 5.1 Z.ai | MXFP4 | won't run | 426.6 GB | – | – | – | – |
| GLM 5.2 Z.ai | UD-Q4_K_M | won't run | 440.5 GB | – | – | – | – |
| GLM 5.3 Z.ai | Q8_0 | won't run | 753.0 GB | – | – | – | – |
| Kimi K2 Moonshot AI | Q4_K_M | won't run | 583.6 GB | – | – | – | – |
| Kimi K2 Instruct 0905 Moonshot AI | Q4_K_M | won't run | 584.0 GB | – | – | – | – |
| Kimi K2 Thinking Moonshot AI | Q4_K_M | won't run | 584.0 GB | – | – | – | – |
| Kimi K2.5 Moonshot AI | Q4_K_M | won't run | 584.0 GB | – | – | – | – |
| MiniMax M2 MiniMax | Q4_K_M | won't run | 145.5 GB | – | – | – | – |
| MiniMax M2.1 MiniMax | Q4_K_M | won't run | 145.5 GB | – | – | – | – |
| MiniMax M2.5 MiniMax | MXFP4 | won't run | 131.9 GB | – | – | – | – |
| MiniMax M3 MiniMax | UD-Q4_K_M | won't run | 255.4 GB | – | – | – | – |
| Mistral Medium 3.5 128B Mistral AI | Q4_K_M | won't run | 92.9 GB | – | – | – | – |
Specifications
From the manufacturer's published specifications; sources are linked where we have them.
- GPU
- Arc Pro B60
- Memory
- 24 GB GDDR6
- Memory bus
- 192-bit
- Memory bandwidth
- 456 GB/s
- FP16 compute
- 98.5 TFLOPS
- Software
- SYCL / oneAPI
- Board power
- 200 W
- PCIe generation
- Gen 5
- PCIe lanes
- x8
Compare with
Questions
- How much memory does the Intel Arc Pro B60 have for AI models?
- The Intel Arc Pro B60 has 24 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 Pro B60 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. 40 of the 113 models we track fit at that context.
- Can the Intel Arc Pro B60 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 Pro B60 and system RAM can hold.
- How much does the Intel Arc Pro B60 cost in Canada?
- The best new price for the Intel Arc Pro B60 in Canada is $985 at Amazon.
Speeds on this page are for 64k context. See the best hardware for local AI at every budget.