CoolFace
Modelpublic

prithivMLmods/Q3.5-9B-GLM-5.1-DA-GGUF

sourceHugging Faceapache-2.0updated 4mo agoView on Hugging Face
2likes599downloads
Model Card

Q3.5-9B-GLM-5.1-DA-GGUF

Q3.5-9B-GLM-5.1-DA (Qwen3.5 GLM Distilled-Abliterated) is a reasoning-focused model built on top of Qwen/Qwen3.5-9B through the prithivMLmods/Qwen3.5-9B-Unredacted-MAX base. The model is optimized for long-context mathematical reasoning, structured problem solving, and context-aware generation using distilled reasoning traces derived from GLM-5.1 reasoning datasets combined with refusal direction analysis and ablation-based training strategies to reduce internal refusal behaviors while preserving strong reasoning and instruction-following performance.
[!IMPORTANT] This model is intended strictly for research and learning purposes. Due to reduced internal refusal mechanisms, it may generate sensitive or unrestricted content. Users assume full responsibility for how the model is used. The authors and hosting platform disclaim any liability for generated outputs.
[!NOTE] Note: This model is experimental and may generate artifacts.

Model Files

File NameQuant TypeFile SizeFile Link
Q3.5-9B-GLM-5.1-DA.BF16.ggufBF1617.9 GBDownload
Q3.5-9B-GLM-5.1-DA.F16.ggufF1617.9 GBDownload
Q3.5-9B-GLM-5.1-DA.Q2_K.ggufQ2_K3.83 GBDownload
Q3.5-9B-GLM-5.1-DA.Q3KL.ggufQ3KL4.93 GBDownload
Q3.5-9B-GLM-5.1-DA.Q3KM.ggufQ3KM4.62 GBDownload
Q3.5-9B-GLM-5.1-DA.Q3KS.ggufQ3KS4.26 GBDownload
Q3.5-9B-GLM-5.1-DA.Q4_0.ggufQ4_05.31 GBDownload
Q3.5-9B-GLM-5.1-DA.Q4KM.ggufQ4KM5.63 GBDownload
Q3.5-9B-GLM-5.1-DA.Q4KS.ggufQ4KS5.35 GBDownload
Q3.5-9B-GLM-5.1-DA.Q5_0.ggufQ5_06.31 GBDownload
Q3.5-9B-GLM-5.1-DA.Q5KM.ggufQ5KM6.47 GBDownload
Q3.5-9B-GLM-5.1-DA.Q5KS.ggufQ5KS6.31 GBDownload
Q3.5-9B-GLM-5.1-DA.Q6_K.ggufQ6_K7.36 GBDownload
Q3.5-9B-GLM-5.1-DA.Q8_0.ggufQ8_09.53 GBDownload
Q3.5-9B-GLM-5.1-DA.mmproj-bf16.ggufmmproj-bf16922 MBDownload
Q3.5-9B-GLM-5.1-DA.mmproj-f16.ggufmmproj-f16922 MBDownload
Q3.5-9B-GLM-5.1-DA.mmproj-q8_0.ggufmmproj-q8_0624 MBDownload

## Quants Usage

(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)

Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better):

image.png