on

Can the Intel Arc Pro B70 run Qwen3-VL 30B-A3B Thinking?

73Great quality (A) · 73 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking.

Yes, it runs great

Runs great. At Q5_K_M it needs about 25.1 GB of 32.0 GB usable, with an estimated speed of 95.2 tok/s.

Best quant
Q5_K_M
Generation speed
95.2 tok/s
Prompt processing
6,233 tok/s
First token (1K prompt)
0.3 s
Largest safe context
76K

Best app to run it on the Intel Arc Pro B70

On Windows

llama.cpp

Command line + local API · runs on llama.cpp

  • Supports Intel Arc through SYCL and Vulkan.
  • Usually the first to support new model architectures.
llama-server -hf Qwen/Qwen3-VL-30B-A3B-Thinking-GGUF:Q5_K_M
  • LM Studio Point-and-click: search, download and chat in one window.
  • Ollama Intel GPU support here is experimental (Vulkan).

On Linux

llama.cpp

Command line + local API · runs on llama.cpp

  • Supports Intel Arc through SYCL and Vulkan.
  • Usually the first to support new model architectures.
llama-server -hf Qwen/Qwen3-VL-30B-A3B-Thinking-GGUF:Q5_K_M
  • LM Studio Point-and-click: search, download and chat in one window.
  • Ollama Intel GPU support here is experimental (Vulkan).

How we choose: the files published for this model, your operating system and GPU, whether it fits fully in memory, and published speed tests (MLX vs llama.cpp on Apple silicon, vLLM vs llama.cpp vs Ollama on NVIDIA). Details.

Download Qwen3-VL 30B-A3B Thinking

Quickest · Ollama

One command downloads a ready-to-run version and starts a chat.

Get Ollama at ollama.com/download (opens in a new tab) · model page (opens in a new tab)

ollama run qwen3-vl:30b-a3b-thinking

Quantized files · GGUF

Works in LM Studio, llama.cpp, Jan and Ollama. No sign-in needed.

huggingface.co/Qwen/Qwen3-VL-30B-A3B-Thinking-GGUF (opens in a new tab)

ollama run hf.co/Qwen/Qwen3-VL-30B-A3B-Thinking-GGUF

Original weights · Hugging Face

Full-precision files from Alibaba, for fine-tuning, vLLM, Transformers.

huggingface.co/Qwen/Qwen3-VL-30B-A3B-Thinking (opens in a new tab)

No sign-in needed.

Links checked 3 days ago against Hugging Face, Ollama and GitHub.

How it’s rated

Quality 73Great quality (A) · 73 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking.
How capable the model itself is at Q5_K_M, from its editorial quality tier scaled by the quantization or precision. It’s the same on any hardware that runs this variant. Scale: A+ 85+ · A 70+ · B 55+ · C 40+ · D under 40.
Runs Runs great
How well it runs on the Intel Arc Pro B70: speed, capped by how well it fits in memory. Runs great: 30+ tokens/s (or near the image, video or decision speed target) · Runs well: 10+ tokens/s · Slow: 3+ tokens/s · Very slow: under 3 · Won’t run: doesn’t fit even with offload. A tight fit or RAM offload caps it at Runs well; heavy offload caps it at Slow.

Match score

To order lists, each result also gets a match score out of 100 from four parts. It favors the most capable model that still runs well.

Model qualityEditorial quality tier of the model, scaled by the quantization or precision used.33.2 / 45
Memory fitFull marks when everything sits in GPU memory; fewer when part spills to system RAM.25.0 / 25
SpeedGeneration speed against a 40 tokens/s target for LLMs, or render time against a target for image and video.15.0 / 15
Memory useRewards using the memory you have, so a bigger, better variant beats a tiny one that leaves most memory idle.15.0 / 15
Match score88.2 / 100

The match score orders results; it is not shown as a grade. Quality and Runs are the two ratings in the tables.

Every quantization on the Intel Arc Pro B70

Quant Memory needed Available Speed Runs Quality Download
Q2_K 15.4 GB 32.0 GB 150 tok/s Runs great 53Fair quality (C) · 53 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. GGUF files (opens in a new tab)
Q3_K_M 18.2 GB 32.0 GB 130 tok/s Runs great 63Good quality (B) · 63 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. GGUF files (opens in a new tab)
Q4_K_M 22.0 GB 32.0 GB 109 tok/s Runs great 72Great quality (A) · 72 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking. GGUF (opens in a new tab)
Q5_K_M 25.1 GB 32.0 GB 95.2 tok/s Runs great 73Great quality (A) · 73 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking. GGUF files (opens in a new tab)
Q6_K 28.5 GB 32.0 GB 83.7 tok/s Runs welltight fit 75Great quality (A) · 75 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking. GGUF files (opens in a new tab)
Q8_0 35.9 GB 32.0 GB 42.9 tok/s Runs welloffloads to RAM 76Great quality (A) · 76 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. GGUF (opens in a new tab)
F16 65.1 GB 32.0 GB — Won't run 76Great quality (A) · 76 of 100: how capable the model is at F16, whatever it runs on. Match score 10/100 (quality, fit, speed and memory use) sets the ranking. GGUF · part 1 of 2 (opens in a new tab) Original weights (opens in a new tab)

Memory figures assume 8K of context. Longer conversations or documents grow the KV cache.

Other hardware that runs it

Quick answers

How much memory does Qwen3-VL 30B-A3B Thinking need on the Arc Pro B70 32GB?

At Q5_K_M it needs about 25.1 GB. The Arc Pro B70 32GB has 32.0 GB usable.

How fast is Qwen3-VL 30B-A3B Thinking on the Arc Pro B70 32GB?

About 95.2 tok/s at Q5_K_M, an estimate from the hardware’s memory bandwidth and the size of the model.

Which quantization of Qwen3-VL 30B-A3B Thinking should I use on the Arc Pro B70 32GB?

Q5_K_M. Of the versions that fit, it is the one that runs best; when two run equally well, the check prefers the higher-rated one.

Estimates come from published hardware specs and our open formulas, not from running the model on your machine. Real speed varies with runtime, drivers and settings. Numbers marked “Measured” come from a linked benchmark.

Was this page helpful?