Best Local AI Models for Intel Arc A750 (8 GB VRAM)

Q: What is the VRAM and memory bandwidth of the Intel Arc A750?

The Intel Arc A750 features 8 GB of VRAM and a memory bandwidth of 512 GB/s (GDDR6 256-bit). In local language model inference, VRAM determines which model sizes fit on the card, while memory bandwidth dictates how many tokens per second the GPU generates.

Q: What is the best local AI model to run on a Intel Arc A750?

The best overall model for the Intel Arc A750 is Qwen/Qwen3-8B-GGUF using the recommended Q6_K quantization (7.63 GB total memory). With 8 GB of VRAM, this GPU typically runs a 7–8B model at Q6, entirely in VRAM at full GPU speed. Check our guide to the best LLMs for 8 GB VRAM for details.

The Intel Arc A750 has 8 GB of VRAM. Here are the popular AI models it can run locally (4,096-token context, ~16.0 GB system RAM assumed), ranked by popularity.

Verdict: 8 GB of GDDR6 on a wide 256-bit bus at 512 GB/s: 7B–9B models fit in VRAM in 4-bit quantization and run quickly; 12B and larger spill into system RAM. Local LLM support depends on Intel's SYCL, Vulkan or IPEX-LLM backends.

VRAM & Memory

8 GB

GDDR6 256-bit

Bandwidth

512 GB/s

Xe-HPG

Fits in VRAM

25 models

Zero offload

TDP / Assumed RAM

225W

RAM: 16.0 GB

At a glance — 25 of the 36 most popular models run fully in VRAM on the Intel Arc A750 (8 GB), with about 85 tokens/s estimated on an 8B model in Q4. A solid pick is Qwen/Qwen3-8B-GGUF (Q6_K, 7.63 GB, ~81.7 t/s estimated).

The Intel Arc A750 is built on Intel's Xe-HPG architecture featuring GDDR6 256-bit delivering 512 GB/s of raw memory bandwidth. 8 GB of GDDR6 on a wide 256-bit bus at 512 GB/s: 7B–9B models fit in VRAM in 4-bit quantization and run quickly; 12B and larger spill into system RAM. Local LLM support depends on Intel's SYCL, Vulkan or IPEX-LLM backends.

Equipped with 8 GB of dedicated VRAM, the Intel Arc A750 can run 25 popular open-source models completely in GPU memory without offloading. This includes full-speed execution for weights like Qwen3-8B-GGUF, Qwen3-4B-GGUF, Qwen2.5-7B-Instruct-GGUF. For a comprehensive breakdown of compatible model weights, see our guide to the best LLMs for 8 GB VRAM.

With a memory bandwidth of 512 GB/s, this card can generate tokens at an estimated peak rate of ~85.3 tokens/second on an 8B parameter model (Q4_K_M). Its rated power draw is 225W TDP, so ensure your system's power supply and case ventilation are adequate for sustained local inferencing.

New to this? Read: How much VRAM do you need?

How the Intel Arc A750 compares with similar cards

Compared with the NVIDIA RTX 2080 Super, the Intel Arc A750 has the same 8 GB of VRAM, so the same models fit fully on the GPU; about 3% faster token generation (~85 vs ~83 tokens/s on an 8B model in Q4, from 512 vs 496 GB/s); a lower board power (225 vs 250 W) and a different architecture (Xe-HPG vs Turing). Side-by-side comparison
Compared with the NVIDIA RTX 2070 Super/2060 Super, the Intel Arc A750 has the same 8 GB of VRAM, so the same models fit fully on the GPU; about 14% faster token generation (~85 vs ~75 tokens/s on an 8B model in Q4, from 512 vs 448 GB/s); a higher board power (225 vs 215 W) and a different architecture (Xe-HPG vs Turing). Side-by-side comparison
Compared with the NVIDIA RTX 3060 Ti, the Intel Arc A750 has the same 8 GB of VRAM, so the same models fit fully on the GPU; about 14% faster token generation (~85 vs ~75 tokens/s on an 8B model in Q4, from 512 vs 448 GB/s); a higher board power (225 vs 200 W) and a different architecture (Xe-HPG vs Ampere). Side-by-side comparison

Token speeds here are a conservative estimate (memory bandwidth ÷ 6, for an 8B model in Q4 that reads about 5 GB of weights per token, plus overhead); prompt processing depends on GPU compute instead.

25 fit fully in VRAM · 11 run with offload

Only show models that fit fully in VRAM

Model	Size	Quant.	Quality	Memory	Speed~	Verdict
Qwen/Qwen3-8B-GGUF	8.19B	Q6_K	Excellent	7.63 GB	81.7 t/s	Fits in VRAM
Qwen/Qwen3-4B-GGUF	4.02B	Q8_0	Excellent	5.35 GB	128.4 t/s	Fits in VRAM
Qwen/Qwen2.5-7B-Instruct-GGUF	7.62B	Q6_K	Excellent	6.84 GB	87.9 t/s	Fits in VRAM
unsloth/NVIDIA-Nemotron-3.5-Bolt-E4B-GGUF	8.0B	Q6_K_XL	Excellent	7.62 GB	75.7 t/s	Fits in VRAM
Qwen/Qwen2.5-1.5B-Instruct-GGUF	1.54B	GGUF	Excellent	4.23 GB	154.4 t/s	Fits in VRAM
unsloth/LFM2.5-24B-A2B-GGUF	23.97B	IQ2_M	Very low	7.9 GB	73.0 t/s	Fits in VRAM
Qwen/Qwen2.5-0.5B-Instruct-GGUF	0.49B	GGUF	Excellent	2.03 GB	434.1 t/s	Fits in VRAM
unsloth/Ornith-1.0-9B-GGUF	—	Q6_K	Excellent	7.89 GB	73.5 t/s	Fits in VRAM
Qwen/Qwen2.5-Coder-7B-Instruct-GGUF	7.62B	Q6_K	Excellent	6.84 GB	87.9 t/s	Fits in VRAM
ggml-org/gpt-oss-120b-GGUF	116.83B	BF16	Very low	2.42 GB	346.5 t/s	Fits in VRAM
LiquidAI/LFM3-1.7B-GGUF	1.73B	BF16	Excellent	4.08 GB	158.6 t/s	Fits in VRAM
janhq/Jan-v3.5-4B-gguf	4.41B	Q8_0	Excellent	5.73 GB	117.1 t/s	Fits in VRAM
Qwen/Qwen2.5-3B-Instruct-GGUF	3.09B	GGUF	Excellent	7.27 GB	80.8 t/s	Fits in VRAM
bartowski/Meta-Llama-3.1-8B-Instruct-GGUF	8.03B	Q6_K_L	Excellent	7.66 GB	80.3 t/s	Fits in VRAM
unsloth/Llama-3.2-3B-Instruct-GGUF	3.21B	F16	Excellent	7.23 GB	85.4 t/s	Fits in VRAM
LiquidAI/LFM2.5-1.2B-Instruct-GGUF	1.17B	BF16	Excellent	3.03 GB	234.6 t/s	Fits in VRAM
lmstudio-community/gemma-3-1b-it-GGUF	1.0B	Q8_0	Excellent	1.96 GB	514.1 t/s	Fits in VRAM
Qwen/Qwen3-0.6B-GGUF	0.75B	Q8_0	Excellent	1.83 GB	859.7 t/s	Fits in VRAM
bartowski/Qwen_Qwen3-0.6B-GGUF	0.75B	BF16	Excellent	2.64 GB	364.2 t/s	Fits in VRAM
unsloth/Qwen3-1.7B-GGUF	1.72B	BF16	Excellent	4.45 GB	159.5 t/s	Fits in VRAM
LiquidAI/LFM2.5-350M-GGUF	0.35B	BF16	Excellent	1.51 GB	772.7 t/s	Fits in VRAM
Qwen/Qwen2.5-Coder-14B-Instruct-GGUF	14.77B	Q2_K	Low	6.92 GB	95.3 t/s	Fits in VRAM
unsloth/DeepSeek-R1-0528-Qwen3-8B-GGUF	8.19B	Q6_K	Excellent	7.63 GB	81.7 t/s	Fits in VRAM
Qwen/Qwen2.5-Coder-1.5B-Instruct-GGUF	1.54B	Q8_0	Excellent	2.67 GB	290.2 t/s	Fits in VRAM
bartowski/Qwen2.5-14B-Instruct-GGUF	14.77B	IQ3_M	Fair	7.99 GB	79.5 t/s	Fits in VRAM
unsloth/gpt-oss-20b-GGUF	20.91B	F16	Very good	13.74 GB	3.9 t/s	Offload
bartowski/Qwen2.5-32B-Instruct-GGUF	32.76B	Q5_K_L	Very good	23.91 GB	2.3 t/s	Offload
unsloth/Qwen3-Coder-30B-A3B-Instruct-GGUF	30.53B	Q5_K_XL	Very good	21.42 GB	2.5 t/s	Offload
Qwen/Qwen3-14B-GGUF	14.77B	Q8_0	Excellent	16.05 GB	3.4 t/s	Offload
unsloth/flint-GGUF	39.79B	Q3_K_XL	Fair	18.13 GB	2.9 t/s	Offload
unsloth/GLM-4.7-Flash-GGUF	31.22B	Q5_K_XL	Very good	21.21 GB	2.5 t/s	Offload
bartowski/Kwaipilot_KAT-Coder-V2.5-Dev-GGUF	34.66B	Q5_K_S	Very good	23.38 GB	2.2 t/s	Offload
ggml-org/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-GGUF	31.58B	Q4_0	Good	18.42 GB	2.8 t/s	Offload
bartowski/Llama-3.3-70B-Instruct-GGUF	70.55B	IQ2_S	Very low	22.93 GB	2.4 t/s	Offload
unsloth/Qwen3-Coder-Next-GGUF	79.67B	IQ2_XXS	Very low	22.89 GB	2.3 t/s	Offload
bartowski/Nanbeige_Nanbeige4.3-33B-GGUF	33.12B	Q5_K_S	Very good	23.65 GB	2.3 t/s	Offload

"Fits in VRAM" = fast, fully on GPU. "Offload" = part on system RAM, slower. Speed is a rough estimate from the Intel Arc A750's 512 GB/s memory bandwidth (offloaded models are limited by system RAM).

Frequently asked questions

What is the VRAM and memory bandwidth of the Intel Arc A750?

The Intel Arc A750 features 8 GB of VRAM and a memory bandwidth of 512 GB/s (GDDR6 256-bit). In local language model inference, VRAM determines which model sizes fit on the card, while memory bandwidth dictates how many tokens per second the GPU generates.

What is the best local AI model to run on a Intel Arc A750?

The best overall model for the Intel Arc A750 is Qwen/Qwen3-8B-GGUF using the recommended Q6_K quantization (7.63 GB total memory). With 8 GB of VRAM, this GPU typically runs a 7–8B model at Q6, entirely in VRAM at full GPU speed. Check our guide to the best LLMs for 8 GB VRAM for details.

What models can you run on an 8 GB GPU like the Intel Arc A750?

With 8 GB of VRAM, the Intel Arc A750 comfortably runs 7B and 8B models (such as Llama 3.1 8B, Mistral 7B, or Qwen 2.5 7B) using Q4_K_M or Q5_K_M quantizations (~5.5 to 6.8 GB). Running 14B models requires offloading memory to system RAM, which lowers token generation speed.

How do you run local LLMs on an Intel Arc card like the Intel Arc A750?

Intel Arc GPUs run local AI models using the llama.cpp SYCL backend or Intel's IPEX-LLM library. Popular frontends like LM Studio and Ollama provide experimental or DirectML/Vulkan support for Arc hardware.