readygpu

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

For running models locally, priced in Germany. At 32k context the first runs 13 models fully in memory, the second 5.

In short

The Intel Arc A770 16GB has more memory for models: 16 GB against 10 GB. At 32k context the Intel Arc A770 16GB runs 13 of the models we track fully in memory and the NVIDIA GeForce RTX 3080 10GB 5; 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 2.0× as fast as the Intel Arc A770 16GB (estimated, median across models). In Germany the Intel Arc A770 16GB costs 646 € at eBay and the NVIDIA GeForce RTX 3080 10GB 500 € at Amazon: the NVIDIA GeForce RTX 3080 10GB is 146 € cheaper.

Updated . Speeds are estimates; how they are worked out.

Intel Arc A770 16GB

646 €

eBay

Add to build
NVIDIA GeForce RTX 3080 10GB

500 €

Amazon

Add to build

Specifications

SpecIntel Arc A770 16GBNVIDIA GeForce RTX 3080 10GB
GPUArc A770 16GBGeForce RTX 3080 10GB
Memory16 GB GDDR610 GB GDDR6X
Memory bus256-bit320-bit
Memory bandwidth560 GB/s760 GB/s
FP16 compute131 TFLOPS59.5 TFLOPS
SoftwareSYCL / oneAPICUDA
Board power225 W320 W
PCIe generationGen 4Gen 4
PCIe lanesx16x16

What each runs

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

ModelIntel Arc A770 16GBNVIDIA GeForce RTX 3080 10GB
gpt-oss 20B48tok/sMXFP4offload
Gemma 4 12B21tok/sQ8_059tok/sQ4_K_M
Qwen 3.5 9B26tok/sQ8_055tok/sQ6_K
Qwen3 14B20tok/sQ4_K_Moffload
Ministral 3 14B19tok/sQ5_K_Moffload
DeepSeek R1 0528 Qwen3 8B21tok/sQ8_0offload
Qwen3 8B21tok/sQ8_0offload
Qwen 3.5 4B50tok/sQ8_084tok/sQ8_0
Ministral 3 8B21tok/sQ8_0offload
Granite 4.2 8B19tok/sQ8_0offload
Gemma 4 E4B31tok/sQ8_059tok/sQ6_K
LFM2.5 8B-A1B58tok/sQ8_0116tok/sUD-Q6_K
Llama 3.1 8B26tok/sQ6_Koffload
Qwen 3.8 27Boffloadoffload
Qwen 3.5 122B-A10Boffloadwon't run
Qwen 3.6 27Boffloadoffload
Gemma 4 31Boffloadoffload
Mistral Small 4 119Boffloadwon't run
Qwen 3.6 35B-A3Boffloadoffload
Qwen 3.5 27Boffloadoffload
Gemma 4 26B-A4Boffloadoffload
Qwen 3.5 35B-A3Boffloadoffload
GLM 4.7 Flashoffloadoffload
Devstral Small 2 24Boffloadoffload
Nemotron 3.5 Lightning 30B-A3Boffloadoffload
Kimi Linear 48B-A3Boffloadoffload
Qwen3 Coder 30B-A3Boffloadoffload
Qwen3 32Boffloadoffload
Gemma 3 27Boffloadoffload
Mistral Small 3.2 24Boffloadoffload
DeepSeek R1 Distill Qwen 32Boffloadoffload
Phi-4 14Boffloadoffload
DeepSeek V4 Flashwon't runwon't run
GLM 5.3 Flashwon't runwon't run
Qwen 3.8 Flash Nextwon't runwon't run
MiniMax M2.7won't runwon't run
Nemotron 3 Super 120B-A12Bwon't runwon't run
Qwen3 Coder Nextwon't runwon't run
gpt-oss 120Bwon't runwon't run
GLM 4.5 Airwon't runwon't run
Qwen3 Next 80B-A3Bwon't runwon't run
Llama 3.3 70Bwon't runwon'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 NVIDIA GeForce RTX 3080 10GB to spend less.
Which can run bigger models, the Intel Arc A770 16GB or the NVIDIA GeForce RTX 3080 10GB?
At 32k context the Intel Arc A770 16GB runs 13 of the models we track fully in memory and the NVIDIA GeForce RTX 3080 10GB 5; 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 2.0× 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 Germany the Intel Arc A770 16GB costs 646 € at eBay and the NVIDIA GeForce RTX 3080 10GB 500 € at Amazon: the NVIDIA GeForce RTX 3080 10GB is 146 € cheaper.

More comparisons