LA
LG AI Research
Language model · South Korea ·Dec 2024

EXAONE 3.5 32B

Language Open Weights
32B
Parameters
4
Benchmarks

About EXAONE 3.5 32B

EXAONE 3.5 32B is an AI model developed by LG AI Research, in the language category, released in 2024, made available as an open-weights model with 32B params.

On this page you'll find EXAONE 3.5 32B's full specifications, including 4 benchmark results. Review provider pricing and benchmark scores below, or compare EXAONE 3.5 32B head-to-head with other language models.

→ More models by LG AI Research → All language models → AI benchmarks leaderboard

Links

Announcement ↗ Hugging Face ↗

Run EXAONE 3.5 32B locally — what to buy

Share this build ↗

Sized to what EXAONE 3.5 32B actually needs (~8k context at Q4), not to the biggest GPU: Good = cheapest that runs it, Better = best value, Best = most headroom. Speed is a hardware estimate; anything past ~120 tok/s is shown as instant.

Good
AMD Radeon RX 7900 XTX
Consumer GPU · ~$999
~41.3 tok/s
Q4 · fits full context · up to 8k ctx
Runs with: ExLlamaV2, KoboldCpp, LM Studio
See full estimate →
Better
NVIDIA GeForce RTX 4090
Consumer GPU · ~$1,599
~48.9 tok/s
Q4 · fits full context · up to 8k ctx
Runs with: ExLlamaV2, KoboldCpp, LM Studio
See full estimate →
Best
NVIDIA GeForce RTX 5090
Consumer GPU · ~$1,999
~87 tok/s
Q4 · fits full context · up to 8k ctx
Runs with: ExLlamaV2, KoboldCpp, LM Studio
See full estimate →

Software support

·ExLlamaV2 ·KoboldCpp ·LM Studio ·MLX ·Ollama ·SGLang ·TensorRT-LLM ·llama.cpp ·vLLM ?KTransformers ?text-generation-webui

✓ measured · · compatible · — not supported. Informational only — speed is hardware-based.

Consumer GPU
11–87 tok/s
9 options →
Apple
13.7–36.6 tok/s
17 options →
Datacenter GPU
37.1–120+ tok/s
13 options →

Community

Would you run EXAONE 3.5 32B again?
No votes yet — be the first.
Did it run? — community reports by hardware

No reports yet. Own this model on some hardware? Be the first to confirm it runs.

Discussion

No comments yet. Start the discussion.

EXAONE 3.5 32B benchmark scores▶
Compare on the benchmark table →
Benchmark Category Score Variant
AlpacaEval 2 general 60.6% instruct-from-hf-readme
ArenaHard general 78.6% instruct-from-hf-readme
IFEval general 81.7% instruct-from-hf-readme
LiveBench general 43 instruct-from-hf-readme

More models like EXAONE 3.5 32B

AI
DMind-1
 AI
COLLECTIVE-1
 AI
Cogito 1 series
 AI
Euler (Euler大模型)
· 2.5B
 AI
SmolLM-1.7B
· 1.7B
 AI
Llama-3-70B-Synthia-v3.5
· 70B

Frequently asked questions

What is EXAONE 3.5 32B? ▶

EXAONE 3.5 32B is an AI model developed by LG AI Research, in the language category, released in 2024. It is tracked on GenAIList with its specifications, benchmark scores and provider pricing.

Who created EXAONE 3.5 32B? ▶

EXAONE 3.5 32B was developed by LG AI Research and released in 2024.

Is EXAONE 3.5 32B open source or proprietary? ▶

EXAONE 3.5 32B ships as an open-weights model: you can download and self-host the weights, though the licence may place some restrictions on use.

How much does EXAONE 3.5 32B cost? ▶

Pricing for EXAONE 3.5 32B depends on the provider. See the providers table on this page for the latest API rates.

How does EXAONE 3.5 32B perform on benchmarks? ▶

EXAONE 3.5 32B is benchmarked across 4 evaluations on GenAIList, including AlpacaEval 2 (60.6%). See the full benchmark table below and compare it with other models.

No videos yet. Know a good one? Add it below.

Know a great video about EXAONE 3.5 32B?