OpenModelsHQ

EXAONE-3.5-32B-Instruct

LG AI Research (EXAONE)LLMDenseCustom license

EXAONE-3.5-32B-Instruct is an open-weight language model from LG AI Research (EXAONE) with 32B parameters. At 4-bit it needs about 22.8 GB of memory, so the smallest current device that fits it is the Radeon AI PRO R9700.

Overview

Estimated memory at 4-bit
22.8GB

Includes room for an 8k context and runtime overhead. More context needs more memory.

Total parameters
32B
Dense
Context window
32K
32,768 tokens
Cheapest API, blended / 1M
No hosted API
Weights only

Key information

Lab
LG AI Research (EXAONE)
Released
1 Dec 2024
Parameters
32B
Type
Language
Context
32,768 tokens
HF downloads, 30 days
52,502
View all

Will it run on your hardware?

How we estimate
Memory needed vs devices
EXAONE-3.5-32B-Instruct needs about 22.8 GB at 4-bit, 40.3 GB at 8-bit and 76 GB at 16-bit. At 4-bit it fits GeForce RTX 5090, DGX Spark, Mac Studio M5 Ultra (256GB). Dashed lines are usable memory on each device; a model fits when its estimate stays within 90% of it. Log scale. 8k context.
Memory needed vs devices: data
Estimate or deviceMemory
Q422.8 GB
Q840.3 GB
BF1676 GB
RTX 5060 Ti 16 GB16 GB usable
RTX 5090 32 GB32 GB usable
DGX Spark 128 GB108.8 GB usable
Mac Studio M5 Ultra 256 GB192 GB usable

Single-device memory estimate. Pick a device to update the On your device column.

36 GB usable memory

FormatMemory neededOn your deviceExample hardware
4-bit (Q4)≈ 22.8 GBFits 63%Radeon AI PRO R970032 GB memory
8-bit (Q8)≈ 40.3 GBToo big 112%L40S48 GB memory
16-bit (BF16)≈ 76 GBToo big 211%RTX PRO 6000 Blackwell96 GB memory

Fits means the estimate stays within 90% of usable memory. Tight is above 90% and up to 100%. Too big is above 100%. These are memory checks, not speed or compatibility tests.

Mac allowances are 66% of total RAM up to 36 GB, and 75% above. AI boxes allow 85% because their memory is shared with the operating system.

Where to run it

On a Mac

Start with the MLX files, built for Apple Silicon.

mlx-community/EXAONE-3.5-32B-Instruct-bf16Check your Mac

With GGUF

Choose a file for llama.cpp or a compatible app.

bartowski/EXAONE-3.5-32B-Instruct-GGUFFind compatible hardware

Through an API

No hosted API found.

MLX on Apple SiliconView repository
mlx_lm.generate --model mlx-community/EXAONE-3.5-32B-Instruct-bf16 \
  --prompt "Explain how a transformer works."
GGUF with llama.cppView repository
llama-cli -hf bartowski/EXAONE-3.5-32B-Instruct-GGUF \
  -c 8192 -p "Explain how a transformer works."

Example commands built from the repository ids above. They need a working install of MLX or llama.cpp. We have not run them; check each repository for available files.

More about this model

Frequently asked questions

How much memory does EXAONE-3.5-32B-Instruct need? At an 8k context, about 22.8 GB at 4-bit, 40.3 GB at 8-bit and 76 GB at 16-bit (BF16). A longer context needs more.

Can I run EXAONE-3.5-32B-Instruct on a Mac? The smallest current Mac that fits the 4-bit estimate of 22.8 GB is the Mac mini M5 Pro (48GB). An MLX build is available: mlx-community/EXAONE-3.5-32B-Instruct-bf16.

Does the full context fit? EXAONE-3.5-32B-Instruct supports up to 32,768 tokens of context. Our memory estimates use 8k, so long prompts need more memory than shown.

What does it cost through an API? We did not find a hosted API for this model.

License in plain English

Custom license. This model uses a custom license rather than a standard one. Read it on the model card before using the model commercially. This summary is not legal advice.

Read the license on the model card

OMHQ RigBench

Not yet tested. We show no speed or quality score without a measurement.

Revision history and sources

Last updated . Sources:Hugging Face model card, MLX repository, GGUF repository.