LGAI-EXAONE
K EXAONE 236B A23B (236B parameters) requires approximately 173.4 GB of VRAM with Q4_K_M quantization. For the best balance of quality and speed, we recommend hardware with at least 200 GB of VRAM.
Quick specs
Related models
Quick picks
Best hardware
Run this model
Quantization options
No hardware detected — fit column shows raw VRAM estimates
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 92.0 GB | Low | — |
Q3_K_S | 3 | 115.6 GB | Low | — |
NVFP4 | 4 | 132.2 GB | Medium | — |
Q4_K_M | 4 | 144.0 GB | Medium | — |
Q5_K_M | 5 | 169.9 GB | High | — |
Q6_K | 6 | 193.5 GB | High | — |
Q8_0 | 8 | 252.5 GB | Very High | — |
F16 | 16 | 483.8 GB | Maximum | — |
Hardware compatibility
Computing compatibility...
Memory breakdown
Frequently asked questions
K EXAONE 236B A23B (236B parameters) requires approximately 173.4 GB of VRAM with Q4_K_M quantization. Lower quantizations like Q4_K_M use less memory but may reduce quality.
Yes, AMD Instinct MI350X 288GB can run K EXAONE 236B A23B with a compatibility score of 54/100. It provides 288 GB of memory and achieves approximately 40.6 tokens per second.
The recommended quantization for K EXAONE 236B A23B is Q4_K_M, which offers the best balance between model quality and memory efficiency. Higher quantizations preserve more quality but require more VRAM.
The top recommended hardware for K EXAONE 236B A23B: AMD Instinct MI350X 288GB (score: 54/100), AMD Instinct MI325X 256GB (score: 53/100), NVIDIA GB200 192GB (score: 51/100). These provide the best combination of memory, bandwidth, and compute for running this model locally.
Yes, K EXAONE 236B A23B is well-suited for chat. It was designed with these use cases in mind.
See also
