Check my GPU

LLMs ·

EXAONE 4.5 33B

Parameters
34B
Architecture
Dense
Max context
256K tokens
License
exaone
Released
2026-04

How to run it

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 6 days ago against Hugging Face, Ollama and GitHub.

Memory needed

Weights plus KV cache and runtime overhead. Leave a little extra free for the operating system and other apps.

KV cache: sliding-window hybrid: the KV estimate counts the global-attention layers plus a small allowance for the sliding-window layers.

Quantization Quality Weights Total at 8K context Total at 32K context Download
Q2_K Low 13.7 GB 15.1 GB 17.3 GB GGUF files (opens in a new tab)
Q3_K_M Low 16.8 GB 18.2 GB 20.4 GB GGUF files (opens in a new tab)
Q4_K_M Good 21.0 GB 22.3 GB 24.5 GB GGUF (opens in a new tab)
Q5_K_M High 24.4 GB 25.7 GB 27.9 GB GGUF (opens in a new tab)
Q6_K High 28.2 GB 29.5 GB 31.7 GB GGUF (opens in a new tab)
Q8_0 Very high 36.4 GB 37.7 GB 40.0 GB GGUF (opens in a new tab)
F16 Full 68.7 GB 70.0 GB 72.3 GB GGUF (opens in a new tab) Original weights (opens in a new tab)

Best hardware for EXAONE 4.5 33B

The least expensive GPU in our catalog that runs it without offloading is the AMD Radeon RX 7600 XT (launch price $329) at Q2_K.

Grade · points Hardware Quant Memory Speed Fit
90 ptsExcellent (S) · 90 of 100 points: Model quality 36.5/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15 NVIDIA GeForce RTX 5090 Q6_K 31.1 GB / 32.0 GB 44.4 tok/s Tight fit
88 ptsExcellent (S) · 88 of 100 points: Model quality 35.1/45, Memory fit 24.0/25, Speed 14.2/15, Memory use 15.0/15 NVIDIA GeForce RTX 4090 Q4_K_M 23.5 GB / 24.0 GB 36.0 tok/s Tight fit
87 ptsExcellent (S) · 87 of 100 points: Model quality 35.1/45, Memory fit 24.0/25, Speed 13.7/15, Memory use 15.0/15 NVIDIA GeForce RTX 3090 Q4_K_M 23.5 GB / 24.0 GB 33.4 tok/s Tight fit
86 ptsExcellent (S) · 86 of 100 points: Model quality 35.1/45, Memory fit 24.0/25, Speed 12.9/15, Memory use 15.0/15 AMD Radeon RX 7900 XTX Q4_K_M 23.5 GB / 24.0 GB 29.5 tok/s Tight fit
84 ptsGreat (A) · 84 of 100 points: Model quality 36.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 8.2/15 NVIDIA RTX PRO 6000 Blackwell Q6_K 34.3 GB / 96.0 GB 44.4 tok/s Runs well
83 ptsGreat (A) · 83 of 100 points: Model quality 36.5/45, Memory fit 25.0/25, Speed 6.9/15, Memory use 15.0/15 Apple M1 Max (64 GB) Q6_K 33.3 GB / 48.0 GB 8.5 tok/s Runs well
82 ptsGreat (A) · 82 of 100 points: Model quality 35.1/45, Memory fit 25.0/25, Speed 9.7/15, Memory use 12.6/15 Apple M4 Max (64 GB) Q4_K_M 26.1 GB / 48.0 GB 16.8 tok/s Runs well
82 ptsGreat (A) · 82 of 100 points: Model quality 35.8/45, Memory fit 25.0/25, Speed 6.2/15, Memory use 15.0/15 Apple M4 Pro (48 GB) Q5_K_M 28.6 GB / 36.0 GB 6.9 tok/s Runs well
79 ptsGreat (A) · 79 of 100 points: Model quality 25.8/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15 NVIDIA GeForce RTX 4080 SUPER Q2_K 15.9 GB / 16.0 GB 43.2 tok/s Tight fit
79 ptsGreat (A) · 79 of 100 points: Model quality 25.8/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15 NVIDIA GeForce RTX 5070 Ti Q2_K 15.9 GB / 16.0 GB 52.6 tok/s Tight fit

Check it on your own hardware

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.