K-EXAONE 236B-A23B on Apple M3 Ultra (256 GB)

Can the Apple M3 Ultra (256 GB) run K-EXAONE 236B-A23B?

Yes, it runs great

Runs great. At Q4_K_M it needs about 161 GB of 192 GB usable, with an estimated speed of 33.4 tok/s.

Best quant: Q4_K_M
Generation speed: 33.4 tok/s
Prompt processing: 766 tok/s
First token (1K prompt): 1.3 s
Largest safe context: 256K

Best app to run it on the Apple M3 Ultra (256 GB)

On macOS

LM Studio

Desktop app · runs on llama.cpp, MLX · use the MLX build

Runs the MLX build, typically up to 10% faster than GGUF for a model with 23B active parameters on Apple silicon.
Point-and-click: search, download and chat in one window.

Open K-EXAONE 236B-A23B in LM Studio

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

Want an agent? K-EXAONE 236B-A23B 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 K-EXAONE 236B-A23B

Recommended for the Apple M3 Ultra (256 GB): Q4_K_M. 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 Q4_K_M file (opens in a new tab)

huggingface.co/LGAI-EXAONE/K-EXAONE-236B-A23B-GGUF (opens in a new tab)

ollama run hf.co/LGAI-EXAONE/K-EXAONE-236B-A23B-GGUF:Q4_K_M

Original weights · Hugging Face

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

huggingface.co/LGAI-EXAONE/K-EXAONE-236B-A23B (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/K-EXAONE (opens in a new tab)

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

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

How it’s rated

Quality 83Great quality (A) · 83 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking.: How capable the model itself is at Q4_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 Apple M3 Ultra (256 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.	37.6 / 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.	25.0 / 25
SpeedGeneration speed against a 40 tokens/s target for LLMs, or render time against a target for image and video.	13.7 / 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	91.3 / 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 Apple M3 Ultra (256 GB)

Quant	Memory needed	Available	Speed	Runs	Quality	Download
`Q2_K`	111 GB	192 GB	51.8 tok/s	Runs great	61Good quality (B) · 61 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking.	GGUF files (opens in a new tab)
`Q3_K_M`	133 GB	192 GB	42.0 tok/s	Runs great	73Great quality (A) · 73 of 100: how capable the model is at Q3_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)
`Q4_K_M`	161 GB	192 GB	33.4 tok/s	Runs great	83Great quality (A) · 83 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q5_K_M`	185 GB	192 GB	28.0 tok/s	Runs welltight fit	85Excellent quality (A+) · 85 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q6_K`	211 GB	192 GB	20.3 tok/s	Runs wellover GPU memory limit	87Excellent quality (A+) · 87 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q8_0`	268 GB	192 GB	—	Won't run	88Excellent quality (A+) · 88 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`	491 GB	192 GB	—	Won't run	88Excellent quality (A+) · 88 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

73Great quality (A) · 73 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking. Apple M2 Ultra (192 GB) Q3_K_M · 41.2 tok/s · Runs well (tight fit)
83Great quality (A) · 83 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. Apple M3 Ultra (512 GB) Q4_K_M · 33.4 tok/s · Runs great
61Good quality (B) · 61 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GB10 (128 GB) Q2_K · 22.3 tok/s · Runs well (tight fit)
61Good quality (B) · 61 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. NVIDIA RTX PRO 6000 Blackwell Q2_K · 56.8 tok/s · Runs well (offloads to RAM)
61Good quality (B) · 61 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. Apple M4 Max (128 GB) Q2_K · 31.0 tok/s · Runs well (over GPU memory limit)
61Good quality (B) · 61 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA RTX Spark N1X (6144-core GPU) (128 GB) Q2_K · 20.7 tok/s · Runs well (over GPU memory limit)

Quick answers

How much memory does K-EXAONE 236B-A23B need on the M3 Ultra 256GB?

At Q4_K_M it needs about 161 GB. The M3 Ultra 256GB has 192 GB usable.

How fast is K-EXAONE 236B-A23B on the M3 Ultra 256GB?

About 33.4 tok/s at Q4_K_M, an estimate from the hardware’s memory bandwidth and the size of the model.

Which quantization of K-EXAONE 236B-A23B should I use on the M3 Ultra 256GB?

Q4_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.