on

Can the NVIDIA RTX 4000 Ada Generation run EXAONE Deep 32B?

62Good quality (B) · 62 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking.

Yes, it runs well (tight fit)

Runs well (tight fit). At Q3_K_M it needs about 19.4 GB of 20.0 GB usable, with an estimated speed of 17.9 tok/s.

Best quant
Q3_K_M
Generation speed
17.9 tok/s
Prompt processing
601 tok/s
First token (1K prompt)
1.7 s
Largest safe context
10K

Best app to run it on the NVIDIA RTX 4000 Ada Generation

On Windows

Ollama

Command line + local API · runs on llama.cpp (ggml), MLX (Apple silicon, preview)

  • One command with Ollama’s own build of this model.
  • Serves an OpenAI-compatible API that other apps and coding tools can use.
ollama run exaone-deep:32b
  • LM Studio Point-and-click: search, download and chat in one window.
  • llama.cpp Usually the first to support new model architectures.

On Linux

Ollama

Command line + local API · runs on llama.cpp (ggml), MLX (Apple silicon, preview)

  • One command with Ollama’s own build of this model.
  • Serves an OpenAI-compatible API that other apps and coding tools can use.
ollama run exaone-deep:32b
  • LM Studio Point-and-click: search, download and chat in one window.
  • llama.cpp Usually the first to support new model architectures.

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 Deep 32B

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 exaone-deep:32b

Quantized files · GGUF

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

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

ollama run hf.co/LGAI-EXAONE/EXAONE-Deep-32B-GGUF

Original weights · Hugging Face

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

huggingface.co/LGAI-EXAONE/EXAONE-Deep-32B (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 62Good quality (B) · 62 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking.
How capable the model itself is at Q3_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 welltight fit
How well it runs on the NVIDIA RTX 4000 Ada Generation: 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.28.0 / 45
Memory fitFull marks when everything sits in GPU memory; fewer when part spills to system RAM.24.0 / 25
SpeedGeneration speed against a 40 tokens/s target for LLMs, or render time against a target for image and video.10.0 / 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 score77.0 / 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 RTX 4000 Ada Generation

Quant Memory needed Available Speed Runs Quality Download
Q2_K 16.5 GB 20.0 GB 22.7 tok/s Runs well 51Fair quality (C) · 51 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. GGUF files (opens in a new tab)
Q3_K_M 19.4 GB 20.0 GB 17.9 tok/s Runs welltight fit 62Good quality (B) · 62 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. GGUF files (opens in a new tab)
Q4_K_M 23.3 GB 20.0 GB 8.0 tok/s Slowoffloads to RAM 70Great quality (A) · 70 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. GGUF (opens in a new tab)
Q5_K_M 26.5 GB 20.0 GB 5.1 tok/s Slowoffloads to RAM 71Great quality (A) · 71 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking. GGUF (opens in a new tab)
Q6_K 30.0 GB 20.0 GB 3.6 tok/s Slowheavy RAM offload 73Great quality (A) · 73 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. GGUF (opens in a new tab)
Q8_0 37.7 GB 20.0 GB 2.1 tok/s Very slowheavy RAM offload 74Great quality (A) · 74 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking. GGUF (opens in a new tab)
F16 67.7 GB 20.0 GB — Won't run 74Great quality (A) · 74 of 100: how capable the model is at F16, whatever it runs on. Match score 9/100 (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 EXAONE Deep 32B need on the NVIDIA RTX 4000 Ada Generation 20GB?

At Q3_K_M it needs about 19.4 GB. The NVIDIA RTX 4000 Ada Generation 20GB has 20.0 GB usable.

How fast is EXAONE Deep 32B on the NVIDIA RTX 4000 Ada Generation 20GB?

About 17.9 tok/s at Q3_K_M, an estimate from the hardware’s memory bandwidth and the size of the model.

Which quantization of EXAONE Deep 32B should I use on the NVIDIA RTX 4000 Ada Generation 20GB?

Q3_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?