K-EXAONE-2.0-750B-A37B
K-EXAONE-2.0-750B-A37B is an open-weight language model from LG AI Research (EXAONE) with 749B parameters (mixture of experts). At 4-bit it needs about 495.3 GB of memory, more than any single device in our directory has.
Overview
Includes room for an 8k context and runtime overhead. More context needs more memory.
Key information
- Lab
- LG AI Research (EXAONE)
- Released
- 29 Jul 2026
- Parameters
- 749B · MoE
- Type
- Language
- Context
- 262,144 tokens
- License
- Apache-2.0
- HF downloads, 30 days
- 14,313
- Repository
- LGAI-EXAONE/K-EXAONE-2.0-750B-A37B
More from LG AI Research (EXAONE)
View allWill it run on your hardware?
How we estimate| Estimate or device | Memory |
|---|---|
| Q4 | 495.3 GB |
| Q8 | 874.5 GB |
| BF16 | 1649.3 GB |
| RTX 5060 Ti 16 GB | 16 GB usable |
| RTX 5090 32 GB | 32 GB usable |
| DGX Spark 128 GB | 108.8 GB usable |
| Mac Studio M5 Ultra 256 GB | 192 GB usable |
Single-device memory estimate. Pick a device to update the On your device column.
36 GB usable memory
| Format | Memory needed | On your device | Example hardware |
|---|---|---|---|
| 4-bit (Q4) | ≈ 495.3 GB | Too big 1376% | No single device in our directory has enough memory |
| 8-bit (Q8) | ≈ 874.5 GB | Too big 2429% | No single device in our directory has enough memory |
| 16-bit (BF16) | ≈ 1649.3 GB | Too big 4581% | No single device in our directory has enough 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
Through an API
No hosted API found.
More about this model
Frequently asked questions
How much memory does K-EXAONE-2.0-750B-A37B need? At an 8k context, about 495.3 GB at 4-bit, 874.5 GB at 8-bit and 1649.3 GB at 16-bit (BF16). A longer context needs more.
Can I run K-EXAONE-2.0-750B-A37B on a Mac? No Mac in our directory has enough usable memory for the 4-bit estimate of 495.3 GB. We have not found a trusted MLX or GGUF build yet.
Does the full context fit? K-EXAONE-2.0-750B-A37B supports up to 262,144 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
Apache-2.0. This license permits commercial use, modification and redistribution, with conditions such as keeping the required notices. This summary is not legal advice.
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.