Which is better for local AI, the Intel Arc A770 16GB or the NVIDIA GeForce RTX 3080 10GB?

Choose the Intel Arc A770 16GB to run bigger models. Choose the NVIDIA GeForce RTX 3080 10GB for speed. Choose the Intel Arc A770 16GB to spend less.

Intel Arc A770 16GB vs NVIDIA GeForce RTX 3080 10GB

For running models locally, priced in the US. At 8k context the first runs 31 models fully in memory, the second 23.

In short

The Intel Arc A770 16GB has more memory for models: 16 GB against 10 GB. At 8k context the Intel Arc A770 16GB runs 31 of the models we track fully in memory and the NVIDIA GeForce RTX 3080 10GB 23; only the Intel Arc A770 16GB holds gpt-oss 20B. On the models both run fully in memory, the NVIDIA GeForce RTX 3080 10GB is about 1.7× as fast as the Intel Arc A770 16GB (estimated, median across models). In the US the Intel Arc A770 16GB costs $400 at Amazon and the NVIDIA GeForce RTX 3080 10GB $469 at Amazon: the Intel Arc A770 16GB is $69 cheaper.

Updated October 16, 2026. Speeds are estimates; how they are worked out.

Intel Arc A770 16GB

$400

Amazon

Add to build

NVIDIA GeForce RTX 3080 10GB

$469

Amazon

Add to build

Specifications

Spec	Intel Arc A770 16GB	NVIDIA GeForce RTX 3080 10GB
GPU	Arc A770 16GB	GeForce RTX 3080 10GB
Memory	16 GB GDDR6	10 GB GDDR6X
Memory bus	256-bit	320-bit
Memory bandwidth	560 GB/s	760 GB/s
FP16 compute	131 TFLOPS	59.5 TFLOPS
Software	SYCL / oneAPI	CUDA
Board power	225 W	320 W
PCIe generation	Gen 4	Gen 4
PCIe lanes	x16	x16

What each runs

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

Model	Intel Arc A770 16GB	NVIDIA GeForce RTX 3080 10GB
gpt-oss 20B	59tok/sMXFP4	offload
Gemma 4 12B	21tok/sQ8_0	53tok/sQ5_K_M
Qwen 3.5 9B	28tok/sQ8_0	61tok/sQ6_K
Ministral 3 14B	23tok/sQ6_K	offload
Qwen3 14B	21tok/sQ6_K	offload
DeepSeek R1 0528 Qwen3 8B	28tok/sQ8_0	59tok/sQ6_K
Qwen3 8B	28tok/sQ8_0	59tok/sQ6_K
Phi-4 14B	20tok/sQ6_K	offload
Qwen 3.5 4B	58tok/sQ8_0	98tok/sQ8_0
Ministral 3 8B	28tok/sQ8_0	58tok/sQ6_K
Granite 4.2 8B	26tok/sQ8_0	53tok/sQ6_K
Gemma 4 E4B	33tok/sQ8_0	56tok/sQ8_0
LFM2.5 8B-A1B	105tok/sQ8_0	228tok/sUD-Q6_K
Llama 3.1 8B	37tok/sQ6_K	61tok/sQ6_K
Qwen2.5 0.5B	443tok/sQ8_0	746tok/sQ8_0
Qwen3.5 0.8B	301tok/sQ8_0	506tok/sQ8_0
Qwen3.5 2B	180tok/sQ5_K_M	303tok/sQ5_K_M
DeepSeek R1 Distill Qwen 1.5B	132tok/sQ8_0	221tok/sQ8_0
MiniCPM5 2B	92tok/sQ8_0	155tok/sQ8_0
LFM2.5 2.6B	83tok/sQ8_0	140tok/sQ8_0
LFM2.5 VL 3B	83tok/sQ8_0	140tok/sQ8_0
granite vision 4.1 4b	65tok/sQ8_0	110tok/sQ8_0
granite 4.2 3b	61tok/sQ8_0	103tok/sQ8_0
Kimi VL A3B	55tok/smlx-6bit	offload
Mellum2.1 12B A2.5B Thinking	55tok/sQ8_0	offload
DeepSeek R1 Distill Qwen 7B	33tok/sQ8_0	55tok/sQ8_0
DeepSeek R1 Distill Llama 8B	29tok/sQ8_0	61tok/sQ6_K
Ministral 3 8B Reasoning 2512	28tok/sQ8_0	65tok/sQ5_K_M
GLM 4.6V Flash	27tok/sQ8_0	73tok/sQ4_K_M
GLM 4.1V 9B Thinking	23tok/smlx-8bit	offload
DeepSeek R1 Distill Qwen 14B	20tok/sQ6_K	offload
Qwen 3.8 27B	offload	offload
Qwen 3.5 122B-A10B	offload	won't run
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
Qwen3 Coder 30B-A3B	offload	offload
Kimi Linear 48B-A3B	offload	offload
Qwen3 32B	offload	offload
Mistral Small 3.2 24B	offload	offload
Gemma 3 27B	offload	offload
DeepSeek R1 Distill Qwen 32B	offload	offload
LFM2.5 24B A2B	offload	offload
Devstral Small 2507	offload	offload
Magistral Small 2506	offload	offload
Magistral Small 2507	offload	offload
Magistral Small 2509	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
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
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 V3 0324	won't run	won't run
DeepSeek V3.1	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 4.5V	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 5.1	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 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 A770 16GB or the NVIDIA GeForce RTX 3080 10GB?: Choose the Intel Arc A770 16GB to run bigger models. Choose the NVIDIA GeForce RTX 3080 10GB for speed. Choose the Intel Arc A770 16GB to spend less.
Which can run bigger models, the Intel Arc A770 16GB or the NVIDIA GeForce RTX 3080 10GB?: At 8k context the Intel Arc A770 16GB runs 31 of the models we track fully in memory and the NVIDIA GeForce RTX 3080 10GB 23; only the Intel Arc A770 16GB holds gpt-oss 20B.
Which is faster for local AI, the Intel Arc A770 16GB or the NVIDIA GeForce RTX 3080 10GB?: On the models both run fully in memory, the NVIDIA GeForce RTX 3080 10GB is about 1.7× as fast as the Intel Arc A770 16GB (estimated, median across models).
What is the price difference between the Intel Arc A770 16GB and the NVIDIA GeForce RTX 3080 10GB?: In the US the Intel Arc A770 16GB costs $400 at Amazon and the NVIDIA GeForce RTX 3080 10GB $469 at Amazon: the Intel Arc A770 16GB is $69 cheaper.

Intel Arc A770 16GB vs NVIDIA GeForce RTX 3080 10GB

In short

Specifications

What each runs

Questions

More comparisons