Can the NVIDIA H100 NVL run EXAONE 4.0 32B?

Yes, it runs great

Runs great. At Q8_0 it needs about 40.0 GB of 94.0 GB usable, with an estimated speed of 76.2 tok/s.

Best quant: Q8_0
Generation speed: 76.2 tok/s
Prompt processing: 2,700 tok/s
First token (1K prompt): 0.4 s
Largest safe context: 128K

Best app to run it on the NVIDIA H100 NVL

On Linux

Inference server · runs on vLLM

The full model fits in GPU memory at 8-bit, so it can batch many requests: best for serving a team or an app.

vllm serve LGAI-EXAONE/EXAONE-4.0-32B

LM Studio Point-and-click: search, download and chat in one window.
SGLang The full model fits in GPU memory at 8-bit, so it can batch many requests: best for serving a team or an app.

On Windows

LM Studio

Desktop app · runs on llama.cpp, MLX

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

Open EXAONE 4.0 32B in LM Studio

llama.cpp Usually the first to support new model architectures.
Ollama Runs the Hugging Face GGUF with ollama run hf.co/…

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 4.0 32B

Recommended for the NVIDIA H100 NVL: Q8_0. Every other quantization has its own download link in the table below.

Quantized files · GGUF

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

Download the Q8_0 file (opens in a new tab)

huggingface.co/LGAI-EXAONE/EXAONE-4.0-32B-GGUF (opens in a new tab)

ollama run hf.co/LGAI-EXAONE/EXAONE-4.0-32B-GGUF:Q8_0

Original weights · Hugging Face

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

huggingface.co/LGAI-EXAONE/EXAONE-4.0-32B (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-4.0 (opens in a new tab)

git clone https://github.com/LG-AI-EXAONE/EXAONE-4.0

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

How it’s rated

Quality 72Great quality (A) · 72 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking.: How capable the model itself is at Q8_0, 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 NVIDIA H100 NVL: 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.	32.4 / 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.	9.8 / 15
Match score	82.2 / 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 NVIDIA H100 NVL

Quant	Memory needed	Available	Speed	Runs	Quality	Download
`Q2_K`	18.8 GB	94.0 GB	246 tok/s	Runs great	50Fair quality (C) · 50 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking.	GGUF files (opens in a new tab)
`Q3_K_M`	21.7 GB	94.0 GB	193 tok/s	Runs great	60Good quality (B) · 60 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking.	GGUF files (opens in a new tab)
`Q4_K_M`	25.6 GB	94.0 GB	150 tok/s	Runs great	68Good quality (B) · 68 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q5_K_M`	28.8 GB	94.0 GB	124 tok/s	Runs great	69Good quality (B) · 69 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q6_K`	32.3 GB	94.0 GB	104 tok/s	Runs great	71Great quality (A) · 71 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q8_0`	40.0 GB	94.0 GB	76.2 tok/s	Runs great	72Great quality (A) · 72 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`F16`	70.0 GB	94.0 GB	35.1 tok/s	Runs great	72Great quality (A) · 72 of 100: how capable the model is at F16, whatever it runs on. Match score 86/100 (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

69Good quality (B) · 69 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5090 Q5_K_M · 56.8 tok/s · Runs great
68Good quality (B) · 68 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4090 Q4_K_M · 38.7 tok/s · Runs well (tight fit)
68Good quality (B) · 68 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 3090 Q4_K_M · 35.9 tok/s · Runs well (tight fit)
68Good quality (B) · 68 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking. AMD Radeon RX 7900 XTX Q4_K_M · 31.7 tok/s · Runs well (tight fit)
71Great quality (A) · 71 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA RTX PRO 6000 Blackwell Q6_K · 47.7 tok/s · Runs great
68Good quality (B) · 68 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. Apple M4 Max (64 GB) Q4_K_M · 18.0 tok/s · Runs well

Quick answers

How much memory does EXAONE 4.0 32B need on the NVIDIA H100 NVL 94GB?

At Q8_0 it needs about 40.0 GB. The NVIDIA H100 NVL 94GB has 94.0 GB usable.

How fast is EXAONE 4.0 32B on the NVIDIA H100 NVL 94GB?

About 76.2 tok/s at Q8_0, an estimate from the hardware’s memory bandwidth and the size of the model.

Which quantization of EXAONE 4.0 32B should I use on the NVIDIA H100 NVL 94GB?

Q8_0. 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.