—per task?
self-host onlyprice
—output speed?
33Kcontext
Alternatives?
ModelScoreCostPer taskWhat changes
ModelScoreCostPer taskWhat changes
Nothing here yet.
ModelScoreCostPer taskWhat changes
ModelScoreCostPer taskWhat changes
ModelScoreCostPer taskWhat changes
LEXAONE 3.5 7.8B InstructOpen-22%——LEXAONE 3.5 2.4B InstructOpen-34%——All LGAI-EXAONE models →Run it yourself
estimateFits on✗ 8 GB (phone, laptop)✗ 16 GB✓ 24 GB GPU · compressed✓ 48 GB GPU · 8-bit✓ 80 GB GPU · full quality
Licenceexaonecommercial use with conditions
Benchmarks
in Chat & KnowledgeFAQ
How much does EXAONE 3.5 32B Instruct cost?›
There is no per-unit API price: self-host only.
Is EXAONE 3.5 32B Instruct free to use?›
There is no free API. The weights are open, so you can run it yourself.
How good is EXAONE 3.5 32B Instruct, and what is it best at?›
#9 of 32 in Chat & Knowledge.
Is EXAONE 3.5 32B Instruct better than Reflection Llama 3.1 70B?›
On MMLU-Pro · official board, EXAONE 3.5 32B Instruct scores 58.9 vs 60.4 — lower.
What is the context window of EXAONE 3.5 32B Instruct?›
33K tokens.
When was EXAONE 3.5 32B Instruct released? Is there a newer version?›
Released 2024-12-01. It is the current version in its line.
Is EXAONE 3.5 32B Instruct open source?›
Yes, the weights are open (exaone licence).
Can I run EXAONE 3.5 32B Instruct locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
Can EXAONE 3.5 32B Instruct read images?›
No, it accepts text only.
What is EXAONE 3.5 32B Instruct?›
EXAONE 3.5 32B Instruct is an open-weights language model from LGAI-EXAONE, released Dec 2024.
What are the best alternatives to EXAONE 3.5 32B Instruct?›
Gemini 3.1 Pro (better), GPT OSS 20B (open weights).