CoolFace
Modelpublic

larue316/Qwen3.6-12B-IQ-Ultra-Heretic-Uncensored-Thinking-V2-Hightop-GGUF

sourceHugging Faceapache-2.0updated 4mo agoView on Hugging Face
1likes895downloads
Model Card

Qwen3.6 12B IQ Ultra Heretic Uncensored Thinking V2 Hightop - GGUF

GGUF quantizations of DavidAU/Qwen3.6-12B-IQ-Ultra-Heretic-Uncensored-Thinking-V2-Hightop.

Converted and quantized using llama.cpp b9192.

Available Quants

QuantSizeQuality
Q8_011.57 GBNear-perfect
Q6_K8.93 GBExcellent
Q5KM7.84 GBVery good
Q5KS7.65 GBVery good
Q5_07.65 GBGood
Q4KM6.82 GBBest balance
IQ4_NL6.58 GBVery good (IQ)
Q4KS6.49 GBGood
Q4_06.43 GBGood
IQ4_XS6.31 GBGood (IQ)
Q3KL5.94 GBAcceptable
Q3KM5.58 GBAcceptable
IQ3_M5.33 GBAcceptable (IQ)
IQ3_S5.27 GBAcceptable (IQ)
Q3KS5.15 GBFair
Q2_K4.60 GBMinimal usable

Original Model

DavidAU/Qwen3.6-12B-IQ-Ultra-Heretic-Uncensored-Thinking-V2-Hightop

Usage

Use with LM Studio, llama.cpp, Ollama, or any GGUF-compatible inference engine.