Downloads · 30 days
49
2% of all-time downloads
sarvam-30b-Uncensored-gguf
ThatCultivator/sarvam-30b-Uncensored-gguf
sarvam-30b-Uncensored-gguf is a text generation model from ThatCultivator. Use it when you need the model to write or continue text. The card lists the license as apache-2.0.
This is the quantized version of the aoxo/sarvam-30b-uncensored model that is a finetune of the base model sarvamai/sarvam-30b.
All-time downloads
2.8K
Public
Repo size
81.3 GB
Likes
3
Public
Repo makeup
Click a slice to open those files.
.gguf61.7 GB · 100%
At a glance
- Task
- Text Generation
- License
- apache-2.0
- Access
- Public
- Created
- Mar 10, 2026
- Updated
- Mar 12, 2026
- SHA
- ceedf701
Try a prompt
Base models
Model card
From the Hugging Face model README
Sarvam-30b-uncensored
This is the quantized version of the aoxo/sarvam-30b-uncensored model that is a finetune of the base model sarvamai/sarvam-30b.
Why use this?
The original finetune is in the bf16 format, which requires significantly stronger hardware than the average consumer-grade hardware. To solve this problem, I have GGUF quantized the finetuned uncensored model and now it can comfortably run on consumer hardware.
Quantization details
Original model size: ~60gb Quantization method: GGUF Q4_K_M, GGUF Q6_K Post-Quantization size: ~19gb, ~26gb
Tested on:
L4 gpu (24gb)
NOTE: I might release other quants like Q8_0 if there's demand.
- Task
- Text Generation
- License
- apache-2.0
- Created
- Mar 10, 2026
- Updated
- Mar 12, 2026