EXAONE 4.5 33B on Intel Core Ultra 200V (Arc 140V) (32 GB)

Can the Intel Core Ultra 200V (Arc 140V) (32 GB) run EXAONE 4.5 33B?

Yes, but slowly (tight fit)

Slow (tight fit). At Q2_K it needs about 16.5 GB of 18.2 GB usable, with an estimated speed of 6.1 tok/s.

Best quant: Q2_K
Generation speed: 6.1 tok/s
Prompt processing: 128 tok/s
First token (1K prompt): 8.0 s
Largest safe context: 26K

Best app to run it on the Intel Core Ultra 200V (Arc 140V) (32 GB)

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 LGAI-EXAONE/EXAONE-4.5-33B-GGUF:Q2_K

LM Studio Point-and-click: search, download and chat in one window.
Jan Point-and-click: search, download and chat in one window.

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 LGAI-EXAONE/EXAONE-4.5-33B-GGUF:Q2_K

LM Studio Point-and-click: search, download and chat in one window.
Jan Point-and-click: search, download and chat in one window.

Want an agent? EXAONE 4.5 33B supports tool use, so you can pair a llama.cpp or MLX LM server with one of these. Apps that run on this computer come first.

Coding agents

Personal assistants

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 EXAONE 4.5 33B

Quantized files · GGUF

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

huggingface.co/LGAI-EXAONE/EXAONE-4.5-33B-GGUF (opens in a new tab)

ollama run hf.co/LGAI-EXAONE/EXAONE-4.5-33B-GGUF

Original weights · Hugging Face

Full-precision files from LG AI Research, for fine-tuning, vLLM, Transformers.

huggingface.co/LGAI-EXAONE/EXAONE-4.5-33B (opens in a new tab)

No sign-in needed.

Official repo · GitHub

Reference code, inference scripts and docs from LG AI Research. The weights themselves download from Hugging Face.

github.com/LG-AI-EXAONE/EXAONE-4.5 (opens in a new tab)

git clone https://github.com/LG-AI-EXAONE/EXAONE-4.5

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

How it’s rated

Quality 57Good quality (B) · 57 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking.: How capable the model itself is at Q2_K, 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 Slowtight fit: How well it runs on the Intel Core Ultra 200V (Arc 140V) (32 GB): 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.	25.8 / 45
Memory fitFull marks when the model fits in the share of unified memory the GPU can use; fewer when it goes past that limit.	24.0 / 25
SpeedGeneration speed against a 40 tokens/s target for LLMs, or render time against a target for image and video.	5.9 / 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 score	70.7 / 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 Core Ultra 200V (Arc 140V) (32 GB)

Quant	Memory needed	Available	Speed	Runs	Quality	Download
`Q2_K`	16.5 GB	18.2 GB	6.1 tok/s	Slowtight fit	57Good quality (B) · 57 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking.	GGUF files (opens in a new tab)
`Q3_K_M`	19.6 GB	18.2 GB	4.1 tok/s	Slowover GPU memory limit	68Good quality (B) · 68 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking.	GGUF files (opens in a new tab)
`Q4_K_M`	23.8 GB	18.2 GB	—	Won't run	77Great quality (A) · 77 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 10/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q5_K_M`	27.2 GB	18.2 GB	—	Won't run	79Great quality (A) · 79 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 10/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q6_K`	31.0 GB	18.2 GB	—	Won't run	81Great quality (A) · 81 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 10/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q8_0`	39.2 GB	18.2 GB	—	Won't run	82Great quality (A) · 82 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 11/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`F16`	71.5 GB	18.2 GB	—	Won't run	82Great quality (A) · 82 of 100: how capable the model is at F16, whatever it runs on. Match score 11/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (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

81Great quality (A) · 81 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5090 Q6_K · 44.4 tok/s · Runs well (tight fit)
77Great quality (A) · 77 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4090 Q4_K_M · 36.0 tok/s · Runs well (tight fit)
77Great quality (A) · 77 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. NVIDIA GeForce RTX 3090 Q4_K_M · 33.4 tok/s · Runs well (tight fit)
77Great quality (A) · 77 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. AMD Radeon RX 7900 XTX Q4_K_M · 29.5 tok/s · Runs well (tight fit)
81Great quality (A) · 81 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA RTX PRO 6000 Blackwell Q6_K · 44.4 tok/s · Runs great
77Great quality (A) · 77 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. Apple M4 Max (64 GB) Q4_K_M · 16.8 tok/s · Runs well

Quick answers

How much memory does EXAONE 4.5 33B need on the Intel Core Ultra 200V (Arc 140V) 32GB?

At Q2_K it needs about 16.5 GB. The Intel Core Ultra 200V (Arc 140V) 32GB has 18.2 GB usable.

How fast is EXAONE 4.5 33B on the Intel Core Ultra 200V (Arc 140V) 32GB?

About 6.1 tok/s at Q2_K, an estimate from the hardware’s memory bandwidth and the size of the model.

Which quantization of EXAONE 4.5 33B should I use on the Intel Core Ultra 200V (Arc 140V) 32GB?

Q2_K. 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.