---
license: mit
base_model: zai-org/GLM-4.6V
base_model_relation: quantized
quantized_by: turboderp
tags:
- exl3
---

EXL3 quants of [GLM-4.6V](https://huggingface.co/zai-org/GLM-4.6V)

⚠️ Requires ExLlamaV3 v0.0.18 (or v0.0.17 `dev` branch)

Base bitrates:

[2.00 bits per weight](https://huggingface.co/turboderp/GLM-4.6V-exl3/tree/2.00bpw)    
[3.00 bits per weight](https://huggingface.co/turboderp/GLM-4.6V-exl3/tree/3.00bpw)    
[4.00 bits per weight](https://huggingface.co/turboderp/GLM-4.6V-exl3/tree/4.00bpw)    
[5.00 bits per weight](https://huggingface.co/turboderp/GLM-4.6V-exl3/tree/5.00bpw)    

Optimized:    

[2.13 bits per weight](https://huggingface.co/turboderp/GLM-4.6V-exl3/tree/2.13bpw)    
[2.32 bits per weight](https://huggingface.co/turboderp/GLM-4.6V-exl3/tree/2.32bpw)    
[2.55 bits per weight](https://huggingface.co/turboderp/GLM-4.6V-exl3/tree/2.55bpw)    
[2.80 bits per weight](https://huggingface.co/turboderp/GLM-4.6V-exl3/tree/2.80bpw)    
[3.13 bits per weight](https://huggingface.co/turboderp/GLM-4.6V-exl3/tree/3.13bpw)    
[3.55 bits per weight](https://huggingface.co/turboderp/GLM-4.6V-exl3/tree/3.55bpw)    
[4.07 bits per weight](https://huggingface.co/turboderp/GLM-4.6V-exl3/tree/4.07bpw)