readygpu

Intel Arc A770 16GB vs NVIDIA GeForce RTX 4070 Ti Super

For running models locally, priced in the UK. At 8k context the first runs 38 models fully in memory, the second 44.

In short

Both have 16 GB of memory for models; the Intel Arc A770 16GB has 560 GB/s of bandwidth and the NVIDIA GeForce RTX 4070 Ti Super 672 GB/s. At 8k context the NVIDIA GeForce RTX 4070 Ti Super runs 44 of the models we track fully in memory and the Intel Arc A770 16GB 38; only the NVIDIA GeForce RTX 4070 Ti Super holds Devstral Small 2 24B. On the models both run fully in memory, the NVIDIA GeForce RTX 4070 Ti Super is about 1.5× as fast as the Intel Arc A770 16GB (estimated, median across models). In the UK the Intel Arc A770 16GB costs £1,354 at Amazon and the NVIDIA GeForce RTX 4070 Ti Super £1,329 at Amazon: the NVIDIA GeForce RTX 4070 Ti Super is £25 cheaper.

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

Intel Arc A770 16GB

£1,354

Amazon

Add to build
NVIDIA GeForce RTX 4070 Ti Super

£1,329

Amazon

Add to build

Specifications

SpecIntel Arc A770 16GBNVIDIA GeForce RTX 4070 Ti Super
GPUArc A770 16GBGeForce RTX 4070 Ti Super
Memory16 GB GDDR616 GB GDDR6X
Memory bus256-bit256-bit
Memory bandwidth560 GB/s672 GB/s
FP16 compute131 TFLOPS88 TFLOPS
SoftwareSYCL / oneAPICUDA
Board power225 W285 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 4070 Ti Super
Devstral Small 2 24Boffload27tok/sQ4_K_M
gpt-oss 20B59tok/sMXFP495tok/sMXFP4
Gemma 4 12B21tok/sQ8_032tok/sQ8_0
Qwen 3.5 9B28tok/sQ8_042tok/sQ8_0
Mistral Small 3.2 24Boffload27tok/sQ4_K_M
Ministral 3 14B23tok/sQ6_K27tok/sQ8_0
Qwen3 14B21tok/sQ6_K31tok/sQ6_K
DeepSeek R1 0528 Qwen3 8B28tok/sQ8_042tok/sQ8_0
Qwen3 8B28tok/sQ8_042tok/sQ8_0
Phi-4 14B20tok/sQ6_K30tok/sQ6_K
Qwen 3.5 4B58tok/sQ8_087tok/sQ8_0
Ministral 3 8B28tok/sQ8_041tok/sQ8_0
Granite 4.2 8B26tok/sQ8_039tok/sQ8_0
Gemma 4 E4B33tok/sQ8_049tok/sQ8_0
LFM2.5 8B-A1B105tok/sQ8_0170tok/sQ8_0
Llama 3.1 8B37tok/sQ6_K54tok/sQ6_K
Qwen2.5 0.5B443tok/sQ8_0660tok/sQ8_0
Qwen3.5 0.8B301tok/sQ8_0447tok/sQ8_0
Qwen3.5 2B180tok/sQ5_K_M268tok/sQ5_K_M
LFM3 1.7B143tok/sQ8_0213tok/sQ8_0
DeepSeek R1 Distill Qwen 1.5B132tok/sQ8_0196tok/sQ8_0
MiniCPM5 2B92tok/sQ8_0137tok/sQ8_0
LFM2.5 2.6B83tok/sQ8_0123tok/sQ8_0
LFM2.5 VL 3B83tok/sQ8_0123tok/sQ8_0
Spark X2.5 4B82tok/smlx-4bit123tok/smlx-4bit
Kimi VL A3B Thinking 250671tok/sQ4_K_M115tok/sQ4_K_M
granite vision 4.1 4b65tok/sQ8_097tok/sQ8_0
Ministral 3 3B Instruct 251262tok/sQ8_092tok/sQ8_0
granite 4.2 3b61tok/sQ8_091tok/sQ8_0
FrogNano 4B 260957tok/sQ8_084tok/sQ8_0
Kimi VL A3B55tok/smlx-6bit90tok/smlx-6bit
Mellum2.1 12B A2.5B Thinking55tok/sQ8_089tok/sQ8_0
DeepSeek R1 Distill Qwen 7B33tok/sQ8_049tok/sQ8_0
GLM 4 9B 041433tok/smlx-5bit49tok/smlx-5bit
DeepSeek R1 Distill Llama 8B29tok/sQ8_043tok/sQ8_0
Ministral 3 8B Reasoning 251228tok/sQ8_041tok/sQ8_0
GLM 4.6V Flash27tok/sQ8_040tok/sQ8_0
GLM 4.1V 9B Thinking23tok/smlx-8bit34tok/smlx-8bit
Ministral 3 14B Reasoning 251223tok/sQ6_K27tok/sQ8_0
DeepSeek R1 Distill Qwen 14B20tok/sQ6_K30tok/sQ6_K
Devstral Small 2507offload27tok/sQ4_K_M
Magistral Small 2506offload27tok/sQ4_K_M
Magistral Small 2507offload27tok/sQ4_K_M
Magistral Small 2509offload27tok/sQ4_K_M
Qwen 3.8 27Boffloadoffload
Qwen 3.5 122B-A10Boffloadoffload
Qwen 3.6 27Boffloadoffload
Gemma 4 31Boffloadoffload
Mistral Small 4 119Boffloadoffload
Qwen 3.6 35B-A3Boffloadoffload
Qwen 3.5 27Boffloadoffload
Gemma 4 26B-A4Boffloadoffload
Qwen 3.5 35B-A3Boffloadoffload
GLM 4.7 Flashoffloadoffload
Nemotron 3.5 Lightning 30B-A3Boffloadoffload
Qwen3 Coder 30B-A3Boffloadoffload
Kimi Linear 48B-A3Boffloadoffload
Qwen3 32Boffloadoffload
Gemma 3 27Boffloadoffload
DeepSeek R1 Distill Qwen 32Boffloadoffload
LFM2.5 24B A2Boffloadoffload
Muse Glimmer 30Boffloadoffload
granite 4.2 30boffloadoffload
Qwen3.8 27B OBLITERATEDoffloadoffload
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
DeepSeek R1won't runwon't run
DeepSeek R1 0528won't runwon't run
DeepSeek R1 Distill Llama 70Bwon't runwon't run
DeepSeek R1 Zerowon't runwon't run
DeepSeek V3won't runwon't run
DeepSeek V3 0324won't runwon't run
DeepSeek V3.1won't runwon't run
DeepSeek V3.1 Terminuswon't runwon't run
DeepSeek V3.2won't runwon't run
DeepSeek V4 Flash 0731won't runwon't run
DeepSeek V4 Flash Vision Expwon't runwon't run
Devstral 2 123B Instruct 2512won't runwon't run
GLM 4.5won't runwon't run
GLM 4.5Vwon't runwon't run
GLM 4.6won't runwon't run
GLM 4.6Vwon't runwon't run
GLM 4.7won't runwon't run
GLM 5won't runwon't run
GLM 5.1won't runwon't run
GLM 5.2won't runwon't run
GLM 5.3won't runwon't run
Kimi Dev 72Bwon't runwon't run
Kimi K2won't runwon't run
Kimi K2 Instruct 0905won't runwon't run
Kimi K2 Thinkingwon't runwon't run
Kimi K2.5won't runwon't run
MiniMax M2won't runwon't run
MiniMax M2.1won't runwon't run
MiniMax M2.5won't runwon't run
MiniMax M3won't runwon't run
Mistral Medium 3.5 128Bwon't runwon't run

Questions

Which is better for local AI, the Intel Arc A770 16GB or the NVIDIA GeForce RTX 4070 Ti Super?
Choose the NVIDIA GeForce RTX 4070 Ti Super to run bigger models. Choose the NVIDIA GeForce RTX 4070 Ti Super for speed. Choose the NVIDIA GeForce RTX 4070 Ti Super to spend less.
Which can run bigger models, the Intel Arc A770 16GB or the NVIDIA GeForce RTX 4070 Ti Super?
At 8k context the NVIDIA GeForce RTX 4070 Ti Super runs 44 of the models we track fully in memory and the Intel Arc A770 16GB 38; only the NVIDIA GeForce RTX 4070 Ti Super holds Devstral Small 2 24B.
Which is faster for local AI, the Intel Arc A770 16GB or the NVIDIA GeForce RTX 4070 Ti Super?
On the models both run fully in memory, the NVIDIA GeForce RTX 4070 Ti Super is about 1.5× 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 4070 Ti Super?
In the UK the Intel Arc A770 16GB costs £1,354 at Amazon and the NVIDIA GeForce RTX 4070 Ti Super £1,329 at Amazon: the NVIDIA GeForce RTX 4070 Ti Super is £25 cheaper.

More comparisons

More hardware for local AI