Carlosian/Qwen3.5-35B-A3B-Abliterated-GGUF overview
Qwen3.5 35B A3B Abliterated — GGUF quant ladder Quantized GGUF builds of Carlosian/Qwen3.5 35B A3B Abliterated https://huggingface.co/Carlosian/Qwen3.5 35B A3B…
Runs locally from ~12.05 GB disk (16 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| Qwen3.5-35B-A3B-Abliterated.Q2_K.gguf | GGUF | GGUF | 12.05 GB | Download |
| Qwen3.5-35B-A3B-Abliterated.Q3_K_M.gguf | GGUF | GGUF | 15.61 GB | Download |
| Qwen3.5-35B-A3B-Abliterated.Q3_K_S.gguf | GGUF | GGUF | 14.14 GB | Download |
| Qwen3.5-35B-A3B-Abliterated.Q4_0.gguf | GGUF | GGUF | 18.36 GB | Download |
| Qwen3.5-35B-A3B-Abliterated.Q4_K_M.gguf | GGUF | GGUF | 19.71 GB | Download |
| Qwen3.5-35B-A3B-Abliterated.Q4_K_S.gguf | GGUF | GGUF | 18.52 GB | Download |
| Qwen3.5-35B-A3B-Abliterated.Q5_K_M.gguf | GGUF | GGUF | 23.03 GB | Download |
| Qwen3.5-35B-A3B-Abliterated.Q5_K_S.gguf | GGUF | GGUF | 22.33 GB | Download |
| Qwen3.5-35B-A3B-Abliterated.Q6_K.gguf | GGUF | GGUF | 26.56 GB | Download |
| Qwen3.5-35B-A3B-Abliterated.Q8_0.gguf | GGUF | GGUF | 34.37 GB | Download |
Model Details
| Model ID | Carlosian/Qwen3.5-35B-A3B-Abliterated-GGUF |
|---|---|
| Author | Carlosian |
| Pipeline | text-generation |
| License | other |
| Base model | Carlosian/Qwen3.5-35B-A3B-Abliterated |
| Last modified | 2026-07-20T12:57:39.000Z |
Model README
---
base_model: Carlosian/Qwen3.5-35B-A3B-Abliterated
base_model_relation: quantized
library_name: gguf
pipeline_tag: text-generation
tags:
- gguf
- quantized
- abliterated
- uncensored
- moe
- llama.cpp
license: other
---
Qwen3.5-35B-A3B-Abliterated — GGUF quant ladder
Quantized GGUF builds of Carlosian/Qwen3.5-35B-A3B-Abliterated for llama.cpp / Ollama / LM Studio.
| Quant | Typical use |
|-------|-------------|
| Q2_K | smallest / extreme low VRAM |
| Q3_K_S / Q3_K_M | low VRAM |
| Q4_0 / Q4_K_S / Q4_K_M | recommended default (Q4_K_M) |
| Q5_K_S / Q5_K_M | higher quality |
| Q6_K | near-lossless |
| Q8_0 | highest quality quant |
Built with llama.cpp on Thunder Compute (A100). Generated 2026-07-20.
Uploaded incrementally per-quant to manage disk (35B MoE ladder is large).
Run Carlosian/Qwen3.5-35B-A3B-Abliterated-GGUF with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models