GraySoft
Projects Models Compare Cloud benchmarks FAQ Download guIDE →
Model Intelligence Sheet

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…

ggufquantizedabliterateduncensoredmoellama.cpptext-generationbase_model:Carlosian/Qwen3.5-35B-A3B-Abliteratedbase_model:quantized:Carlosian/Qwen3.5-35B-A3B-Abliteratedlicense:otherendpoints_compatibleregion:usconversational

Runs locally from ~12.05 GB disk (16 GB VRAM class GPUs with llama.cpp / guIDE).

Downloads
0
Likes
0
Pipeline
text-generation
Author

Repository Files & Downloads

10 GGUF files detected
Direct downloads for local inference
FileTypeQuantizationSizeLink
Qwen3.5-35B-A3B-Abliterated.Q2_K.ggufGGUFGGUF12.05 GBDownload
Qwen3.5-35B-A3B-Abliterated.Q3_K_M.ggufGGUFGGUF15.61 GBDownload
Qwen3.5-35B-A3B-Abliterated.Q3_K_S.ggufGGUFGGUF14.14 GBDownload
Qwen3.5-35B-A3B-Abliterated.Q4_0.ggufGGUFGGUF18.36 GBDownload
Qwen3.5-35B-A3B-Abliterated.Q4_K_M.ggufGGUFGGUF19.71 GBDownload
Qwen3.5-35B-A3B-Abliterated.Q4_K_S.ggufGGUFGGUF18.52 GBDownload
Qwen3.5-35B-A3B-Abliterated.Q5_K_M.ggufGGUFGGUF23.03 GBDownload
Qwen3.5-35B-A3B-Abliterated.Q5_K_S.ggufGGUFGGUF22.33 GBDownload
Qwen3.5-35B-A3B-Abliterated.Q6_K.ggufGGUFGGUF26.56 GBDownload
Qwen3.5-35B-A3B-Abliterated.Q8_0.ggufGGUFGGUF34.37 GBDownload

Model Details

Model IDCarlosian/Qwen3.5-35B-A3B-Abliterated-GGUF
AuthorCarlosian
Pipelinetext-generation
Licenseother
Base modelCarlosian/Qwen3.5-35B-A3B-Abliterated
Last modified2026-07-20T12:57:39.000Z

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.

Download guIDE → · Browse 524k+ models · Compare models

Source: Hugging Face · Compare models