Intel Arc A770 Limited Edition, AI & Machine Learning Benchmarks & Specs

16GB · AI Score 2.0/100 · anchored estimate vs 51 measured cards

2 AI Score Includes estimates

We have not run Intel Arc A770 Limited Edition on our bench. These figures are anchored estimates, interpolated per workload against the 51 GPUs we did measure (confidence: low). On Llama 3.1 8B (Q4_K_M) Intel Arc A770 Limited Edition should deliver about 46.3 tokens/sec. Llama 3.3 70B does not fit. It needs roughly 42GB and this card has 16GB. 2 of the 12 workloads won't fit on 16GB at the tested precision, Qwen3 32B, Llama 3.3 70B. We publish those as hard gates rather than quietly dropping to a smaller quant. Image, video and 3D models aren't listed for this card. They're built for NVIDIA's CUDA, and on Intel Arc they only run through PyTorch XPU workarounds whose speed depends more on the driver and OS than on the card, so we don't estimate them, and they count as not supported in the AI score. For text generation (llama.cpp runs natively on SYCL and Vulkan), the numbers above hold up.

AI & Machine Learning benchmark results

Text Generation tok/s 8

Qwen3 4B71.1

Llama 3.1 8B46.3

Qwen2.5-Coder 14B24.9

Workload	Result	Telemetry	Data
Qwen3 4B	71.1 tok/s	estimated	Est.
Llama 3.1 8B	46.3 tok/s	estimated	Est.
Qwen2.5-Coder 14B	24.9 tok/s	estimated	Est.
Gemma 4 26B A4B	✕ Won't fit needs ~20 GB	VRAM-gated at this precision	Est.
Qwen3 30B A3B	✕ Won't fit needs ~20 GB	VRAM-gated at this precision	Est.
Gemma 4 31B	✕ Won't fit needs ~22 GB	VRAM-gated at this precision	Est.
Qwen3 32B	✕ Won't fit	VRAM-gated at this precision	Est.
Llama 3.3 70B	✕ Won't fit	VRAM-gated at this precision	Est.

How this estimate is derived. This card hasn’t been through our bench yet, so its numbers are anchored estimates, interpolated from the 51 first-party measured cards (Bandwidth Theil-Sen ladder off NVIDIA anchors × vendor factor (LLM ×0.5, diffusion ×0.4); measured VRAM floors; recalibrated 2026-09-19 against published llama.cpp (CUDA/ROCm/Vulkan/SYCL) and Stable Diffusion results.). The VRAM “won’t fit” gates are exact, since they’re pure capacity limits. Confidence: low. Estimates are replaced with measured data as more silicon goes through the bench. Full methodology →

Intel Arc A770 Limited Edition specifications

Architecture	Alchemist (Xe-HPG)
Xe cores	32
VRAM	16GB GDDR6
Memory bus	256-bit
Memory bandwidth	560 GB/s
Boost clock	2,450 MHz
TDP	225 W
Process	6nm
Interface	PCIe 4.0 x16
Release date	2022-09-01
Launch MSRP	$349

Verdict, capable, but 16GB sets the ceiling

Intel Arc A770 Limited Edition scores 2.0/100, #87 of 102. It ran 3 of 12; 2 exceeded its 16GB. Figures are anchored estimates, not measurements, we flag that on every row.

Relative performance: where the Intel Arc A770 Limited Edition lands

100% = this card, AI & Machine Learning headline metric (AI Score). #48 of 61 desktop cards in this vertical.

GPU	%	AI Score
NVIDIA GeForce RTX 2070 SUPER	100%	2
NVIDIA GeForce RTX 2070	100%	2
NVIDIA GeForce RTX 2080 Founders Edition	100%	2
NVIDIA GeForce RTX 3060 Ti	100%	2
Intel Arc A770 Limited Edition	100%	2
NVIDIA GeForce RTX 2060 Super	95%	1.9
GeForce RTX 4060	95%	1.9
NVIDIA GeForce RTX 5050	95%	1.9
NVIDIA GeForce RTX 3050	90%	1.8

One tier up: NVIDIA GeForce RTX 3060 Ti (0%)
One tier down: NVIDIA GeForce RTX 2060 Super (-5%)
Best value alternative ($179): Intel Arc B580 (+5%)

Same card, other workloads: Intel Arc A770 Limited Edition Gaming benchmarks

← All AI & Machine Learning GPU rankings

The silicon

Transistors	21,700 million
Die size	406 mm²
Process node	6 nm
Fabricated by	TSMC
Transistor density	53.4 million per mm²

Denser than 86% of the 746 cards we have silicon data for. Density is the clearest measure of what a process node bought: a card that gained it without growing the die got its speed from the fab rather than the architecture.

Silicon figures from Wikipedia (CC BY-SA 4.0). Benchmarks on this page are our own. Compare every chip.

What this card can build

Whole-job timings, composed from our measured per-model results on this card.

Workflow	Time	Energy	Basis
Full codebase review	40.2 min	n/a	estimate, 0 of 1 stage measured

Can't run: Short social clips (needs Qwen3 32B), 60-second AI short film (needs Qwen3 32B), 24-frame storyboard (needs Qwen3 32B), 6-panel comic page (needs Qwen3 32B), Long-form article batch (needs Llama 3.3 70B).