Which is better for local AI, the Intel Arc B580 or the Intel Arc Pro B60?

Choose the Intel Arc Pro B60 to run bigger models. Choose the Intel Arc B580 to spend less.

Intel Arc B580 vs Intel Arc Pro B60

For running models locally, priced in the UK. At 32k context the first runs 27 models fully in memory, the second 54.

In short

The Intel Arc Pro B60 has more memory for models: 24 GB against 12 GB. At 32k context the Intel Arc Pro B60 runs 54 of the models we track fully in memory and the Intel Arc B580 27; only the Intel Arc Pro B60 holds Qwen 3.8 27B. On the models both run fully in memory, the Intel Arc B580 and the Intel Arc Pro B60 are about as fast as each other (estimated). In the UK the Intel Arc B580 costs £700 at eBay and the Intel Arc Pro B60 £736 at eBay: the Intel Arc B580 is £36 cheaper.

Updated 19 October 2026. Speeds are estimates; how they are worked out.

Intel Arc B580

£700

eBay

Add to build

Intel Arc Pro B60

£736

eBay

Add to build

Specifications

Spec	Intel Arc B580	Intel Arc Pro B60
GPU	Arc B580	Arc Pro B60
Memory	12 GB GDDR6	24 GB GDDR6
Memory bus	192-bit	192-bit
Memory bandwidth	456 GB/s	456 GB/s
FP16 compute	116.5 TFLOPS	98.5 TFLOPS
Software	SYCL / oneAPI	SYCL / oneAPI
Board power	190 W	200 W
PCIe generation	Gen 4	Gen 5
PCIe lanes	x8	x8

What each runs

Estimated decode speed with the most precise quant that fits each one est.

Model	Intel Arc B580	Intel Arc Pro B60
Qwen 3.8 27B	offload	10tok/sQ5_K_M
Qwen 3.6 27B	offload	11tok/sQ5_K_M
Gemma 4 31B	offload	10tok/sQ4_K_M
Qwen 3.6 35B-A3B	offload	48tok/sQ4_K_M
Qwen 3.5 27B	offload	10tok/sQ5_K_M
Gemma 4 26B-A4B	offload	28tok/sQ6_K
Qwen 3.5 35B-A3B	offload	49tok/sQ4_K_M
GLM 4.7 Flash	offload	24tok/sQ5_K_M
Devstral Small 2 24B	offload	10tok/sQ5_K_M
Nemotron 3.5 Lightning 30B-A3B	offload	51tok/sMXFP4
gpt-oss 20B	offload	39tok/sMXFP4
Qwen3 Coder 30B-A3B	offload	25tok/sQ4_K_M
Gemma 4 12B	21tok/sQ6_K	17tok/sQ8_0
Qwen 3.5 9B	21tok/sQ8_0	21tok/sQ8_0
Gemma 3 27B	offload	10tok/sQ5_K_M
Mistral Small 3.2 24B	offload	10tok/sQ5_K_M
Ministral 3 14B	offload	12tok/sQ8_0
Qwen3 14B	offload	11tok/sQ8_0
DeepSeek R1 0528 Qwen3 8B	21tok/sQ5_K_M	17tok/sQ8_0
Qwen3 8B	21tok/sQ5_K_M	17tok/sQ8_0
Phi-4 14B	offload	10tok/sQ8_0
Qwen 3.5 4B	41tok/sQ8_0	41tok/sQ8_0
Ministral 3 8B	22tok/sQ5_K_M	17tok/sQ8_0
Granite 4.2 8B	21tok/sQ4_K_M	16tok/sQ8_0
Gemma 4 E4B	25tok/sQ8_0	25tok/sQ8_0
LFM2.5 8B-A1B	47tok/sQ8_0	47tok/sQ8_0
Llama 3.1 8B	21tok/sQ6_K	21tok/sQ6_K
Qwen2.5 0.5B	244tok/sQ8_0	244tok/sQ8_0
Qwen3.5 0.8B	185tok/sQ8_0	185tok/sQ8_0
Qwen3.5 2B	123tok/sQ5_K_M	123tok/sQ5_K_M
DeepSeek R1 Distill Qwen 1.5B	81tok/sQ8_0	81tok/sQ8_0
MiniCPM5 2B	56tok/sQ8_0	56tok/sQ8_0
Spark X2.5 4B	53tok/smlx-4bit	53tok/smlx-4bit
Mellum2.1 12B A2.5B Thinking	49tok/sQ5_K_M	40tok/sQ8_0
LFM2.5 2.6B	47tok/sQ8_0	47tok/sQ8_0
LFM2.5 VL 3B	47tok/sQ8_0	47tok/sQ8_0
FrogNano 4B 2609	40tok/sQ8_0	40tok/sQ8_0
granite vision 4.1 4b	36tok/sQ8_0	36tok/sQ8_0
granite 4.2 3b	35tok/sQ8_0	35tok/sQ8_0
GLM 4.6V Flash	30tok/sQ4_K_M	20tok/sQ8_0
GLM 4 9B 0414	24tok/smlx-5bit	24tok/smlx-5bit
DeepSeek R1 Distill Qwen 7B	23tok/sQ8_0	23tok/sQ8_0
Ministral 3 8B Reasoning 2512	22tok/sQ5_K_M	17tok/sQ8_0
DeepSeek R1 Distill Llama 8B	21tok/sQ6_K	18tok/sQ8_0
Kimi VL A3B Thinking 2506	offload	30tok/sQ8_0
Kimi VL A3B	offload	29tok/smlx-8bit
LFM2.5 24B A2B	offload	28tok/sQ6_K
GLM 4.1V 9B Thinking	offload	17tok/smlx-8bit
DeepSeek R1 Distill Qwen 14B	offload	10tok/sQ8_0
Devstral Small 2507	offload	10tok/sQ5_K_M
Magistral Small 2506	offload	10tok/sQ5_K_M
Magistral Small 2507	offload	10tok/sQ5_K_M
Magistral Small 2509	offload	10tok/sQ5_K_M
Qwen3.8 27B OBLITERATED	offload	10tok/smlx-4bit
Qwen 3.5 122B-A10B	won't run	offload
Qwen3 Coder Next	won't run	offload
Mistral Small 4 119B	won't run	offload
GLM 4.5 Air	won't run	offload
Qwen3 Next 80B-A3B	won't run	offload
Kimi Linear 48B-A3B	offload	offload
Qwen3 32B	offload	offload
DeepSeek R1 Distill Qwen 32B	offload	offload
granite 4.2 30b	offload	offload
DeepSeek V4 Flash	won't run	won't run
GLM 5.3 Flash	won't run	won't run
Qwen 3.8 Flash Next	won't run	won't run
MiniMax M2.7	won't run	won't run
Nemotron 3 Super 120B-A12B	won't run	won't run
gpt-oss 120B	won't run	won't run
Llama 3.3 70B	won't run	won't run
DeepSeek R1	won't run	won't run
DeepSeek R1 0528	won't run	won't run
DeepSeek R1 Distill Llama 70B	won't run	won't run
DeepSeek R1 Zero	won't run	won't run
DeepSeek V3 0324	won't run	won't run
DeepSeek V3.1	won't run	won't run
DeepSeek V3.1 Terminus	won't run	won't run
DeepSeek V3.2	won't run	won't run
DeepSeek V4 Flash 0731	won't run	won't run
DeepSeek V4 Flash Vision Exp	won't run	won't run
Devstral 2 123B Instruct 2512	won't run	won't run
GLM 4.5	won't run	won't run
GLM 4.5V	won't run	won't run
GLM 4.6	won't run	won't run
GLM 4.6V	won't run	won't run
GLM 4.7	won't run	won't run
GLM 5	won't run	won't run
GLM 5.1	won't run	won't run
GLM 5.2	won't run	won't run
GLM 5.3	won't run	won't run
Kimi Dev 72B	won't run	won't run
Kimi K2	won't run	won't run
Kimi K2 Instruct 0905	won't run	won't run
Kimi K2 Thinking	won't run	won't run
Kimi K2.5	won't run	won't run
MiniMax M2	won't run	won't run
MiniMax M2.1	won't run	won't run
MiniMax M2.5	won't run	won't run
MiniMax M3	won't run	won't run
Mistral Medium 3.5 128B	won't run	won't run

Questions

Which is better for local AI, the Intel Arc B580 or the Intel Arc Pro B60?: Choose the Intel Arc Pro B60 to run bigger models. Choose the Intel Arc B580 to spend less.
Which can run bigger models, the Intel Arc B580 or the Intel Arc Pro B60?: At 32k context the Intel Arc Pro B60 runs 54 of the models we track fully in memory and the Intel Arc B580 27; only the Intel Arc Pro B60 holds Qwen 3.8 27B.
Which is faster for local AI, the Intel Arc B580 or the Intel Arc Pro B60?: On the models both run fully in memory, the Intel Arc B580 and the Intel Arc Pro B60 are about as fast as each other (estimated).
What is the price difference between the Intel Arc B580 and the Intel Arc Pro B60?: In the UK the Intel Arc B580 costs £700 at eBay and the Intel Arc Pro B60 £736 at eBay: the Intel Arc B580 is £36 cheaper.

Intel Arc B580 vs Intel Arc Pro B60

In short

Specifications

What each runs

Questions

More comparisons