---
license: apache-2.0
base_model: openai/gpt-oss-120b
base_model_relation: quantized
quantized_by: turboderp
tags:
- exl3
---

EXL3 quants of [gpt-oss-120b](https://huggingface.co/openai/gpt-oss-120b)

[2.00 bits per weight](https://huggingface.co/turboderp/gpt-oss-120b-exl3/tree/2.00bpw)    
[2.50 bits per weight](https://huggingface.co/turboderp/gpt-oss-120b-exl3/tree/2.50bpw)    
[3.00 bits per weight](https://huggingface.co/turboderp/gpt-oss-120b-exl3/tree/3.00bpw)    
[3.50 bits per weight](https://huggingface.co/turboderp/gpt-oss-120b-exl3/tree/3.50bpw)    
[4.00 bits per weight](https://huggingface.co/turboderp/gpt-oss-120b-exl3/tree/4.00bpw)    

![qb_ppl_vram](https://cdn-uploads.huggingface.co/production/uploads/6383dc174c48969dcf1b4fce/JZUKFMPXU1_vIaVpUsIjJ.png)
![qb_kld_spread_vram](https://cdn-uploads.huggingface.co/production/uploads/6383dc174c48969dcf1b4fce/fldhs99cbGCqA8TmmqNQ5.png)
![qb_kld_hist_combined](https://cdn-uploads.huggingface.co/production/uploads/6383dc174c48969dcf1b4fce/b6d2us43Z67c5dY2Wkhup.png)