Which is better for local AI, the Intel Arc A770 16GB or the Intel Arc B580?

Choose the Intel Arc A770 16GB to run bigger models. Choose the Intel Arc A770 16GB for speed. Choose the Intel Arc B580 to spend less.

Intel Arc A770 16GB vs Intel Arc B580

For running models locally, priced in Germany. At 64k context the first runs 10 models fully in memory, the second 5.

In short

The Intel Arc A770 16GB has more memory for models: 16 GB against 12 GB. At 64k context the Intel Arc A770 16GB runs 10 of the models we track fully in memory and the Intel Arc B580 5; only the Intel Arc A770 16GB holds gpt-oss 20B. On the models both run fully in memory, the Intel Arc A770 16GB is about 1.2× as fast as the Intel Arc B580 (estimated, median across models). In Germany the Intel Arc A770 16GB costs 646 € at eBay and the Intel Arc B580 349 € at eBay: the Intel Arc B580 is 297 € cheaper.

Updated 15 October 2026. Speeds are estimates; how they are worked out.

Intel Arc A770 16GB

646 €

eBay

Add to build

Intel Arc B580

349 €

eBay

Add to build

Specifications

Spec	Intel Arc A770 16GB	Intel Arc B580
GPU	Arc A770 16GB	Arc B580
Memory	16 GB GDDR6	12 GB GDDR6
Memory bus	256-bit	192-bit
Memory bandwidth	560 GB/s	456 GB/s
FP16 compute	131 TFLOPS	116.5 TFLOPS
Software	SYCL / oneAPI	SYCL / oneAPI
Board power	225 W	190 W
PCIe generation	Gen 4	Gen 4
PCIe lanes	x16	x8

What each runs

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

Model	Intel Arc A770 16GB	Intel Arc B580
gpt-oss 20B	38tok/sMXFP4	offload
Gemma 4 12B	20tok/sQ8_0	23tok/sQ5_K_M
Qwen 3.5 9B	24tok/sQ8_0	24tok/sQ6_K
DeepSeek R1 0528 Qwen3 8B	19tok/sQ4_K_M	offload
Qwen3 8B	19tok/sQ4_K_M	offload
Qwen 3.5 4B	42tok/sQ8_0	34tok/sQ8_0
Ministral 3 8B	20tok/sQ4_K_M	offload
Gemma 4 E4B	28tok/sQ8_0	23tok/sQ8_0
LFM2.5 8B-A1B	36tok/sQ8_0	31tok/sUD-Q6_K
Llama 3.1 8B	20tok/sQ5_K_M	offload
Qwen 3.8 27B	offload	offload
Qwen 3.6 27B	offload	offload
Gemma 4 31B	offload	offload
Mistral Small 4 119B	offload	won't run
Qwen 3.6 35B-A3B	offload	offload
Qwen 3.5 27B	offload	offload
Gemma 4 26B-A4B	offload	offload
Qwen 3.5 35B-A3B	offload	offload
GLM 4.7 Flash	offload	offload
Devstral Small 2 24B	offload	offload
Nemotron 3.5 Lightning 30B-A3B	offload	offload
Kimi Linear 48B-A3B	offload	offload
Qwen3 Coder 30B-A3B	offload	offload
Qwen3 32B	offload	offload
Gemma 3 27B	offload	offload
Mistral Small 3.2 24B	offload	offload
DeepSeek R1 Distill Qwen 32B	offload	offload
Ministral 3 14B	offload	offload
Qwen3 14B	offload	offload
Phi-4 14B	offload	offload
Granite 4.2 8B	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
Qwen 3.5 122B-A10B	won't run	won't run
Nemotron 3 Super 120B-A12B	won't run	won't run
Qwen3 Coder Next	won't run	won't run
gpt-oss 120B	won't run	won't run
GLM 4.5 Air	won't run	won't run
Qwen3 Next 80B-A3B	won't run	won't run
Llama 3.3 70B	won't run	won't run

Questions

Which is better for local AI, the Intel Arc A770 16GB or the Intel Arc B580?: Choose the Intel Arc A770 16GB to run bigger models. Choose the Intel Arc A770 16GB for speed. Choose the Intel Arc B580 to spend less.
Which can run bigger models, the Intel Arc A770 16GB or the Intel Arc B580?: At 64k context the Intel Arc A770 16GB runs 10 of the models we track fully in memory and the Intel Arc B580 5; only the Intel Arc A770 16GB holds gpt-oss 20B.
Which is faster for local AI, the Intel Arc A770 16GB or the Intel Arc B580?: On the models both run fully in memory, the Intel Arc A770 16GB is about 1.2× as fast as the Intel Arc B580 (estimated, median across models).
What is the price difference between the Intel Arc A770 16GB and the Intel Arc B580?: In Germany the Intel Arc A770 16GB costs 646 € at eBay and the Intel Arc B580 349 € at eBay: the Intel Arc B580 is 297 € cheaper.

Intel Arc A770 16GB vs Intel Arc B580

In short

Specifications

What each runs

Questions

More comparisons