license: apache-2.0
tags:
- text-generation-inference
- uncensored
- abliterated
- unfiltered
- unredacted
- refusal-ablated
- vllm
- bf16
- max
- alignment-modified
- reasoning
- agent
base_model: - prithivMLmods/Qwen3.6-35B-A3B-abliterated-MAX
language: - en
pipeline_tag: image-text-to-text
library_name: transformers
Qwen3.6-35B-A3B-abliterated-MAX-F32-GGUF
Qwen3.6-35B-A3B-Abliterated-MAX is an abliterated evolution built on top of Qwen/Qwen3.6-35B-A3B. This model applies advanced refusal direction analysis and ablation-based training strategies to reduce internal refusal behaviors while preserving the reasoning and instruction-following strengths of the original architecture. The result is a powerful 35B parameter Mixture-of-Experts language model optimized for detailed responses and improved instruction adherence.
Model Files
| File Name | Quant Type | File Size | File Link |
|---|---|---|---|
| Qwen3.6-35B-A3B-abliterated-MAX.BF16.gguf | BF16 | 69.4 GB | Download |
| Qwen3.6-35B-A3B-abliterated-MAX.F16.gguf | F16 | 69.4 GB | Download |
| Qwen3.6-35B-A3B-abliterated-MAX.F32.gguf | F32 | 139 GB | Download |
| Qwen3.6-35B-A3B-abliterated-MAX.Q8_0.gguf | Q8_0 | 36.9 GB | Download |
| Qwen3.6-35B-A3B-abliterated-MAX.mmproj-bf16.gguf | mmproj-bf16 | 1.66 kB | Download |
| Qwen3.6-35B-A3B-abliterated-MAX.mmproj-f16.gguf | mmproj-f16 | 1.66 kB | Download |
| Qwen3.6-35B-A3B-abliterated-MAX.mmproj-f32.gguf | mmproj-f32 | 1.66 kB | Download |
| Qwen3.6-35B-A3B-abliterated-MAX.mmproj-q8_0.gguf | mmproj-q8_0 | 1.66 kB | Download |
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):
