Get the app
← back to catalog · registered 2026-08-22 13:56

Carlosian/Qwen3.5-35B-A3B-Abliterated-GGUF

Carlosian Qwen 35B GGUF MoE second-order 262K ctx
Your rig guess connected
? Why do I need an app?
Reading your rig…

This is a rough estimate. Install the free app - we'll show exact numbers.

Reading real hardware from your app right now. Numbers below are exact.

Below is the per-quantization compatibility for this model. 

curl -H "Authorization: Bearer $ABL_KEY" \
     "https://abliteration.org/api/v1/models/Carlosian%2FQwen3.5-35B-A3B-Abliterated-GGUF"
Response includes
  • classification m8
  • files 13
  • hub_downloads_all_time 2,142
  • author_summary 4 models
  • readme_text full
Try next
GET/models?author=Carlosian
All 4 models by Carlosian
 GET/models?family=qwen&method=m8
Sibling qwen models · same method
 GET/methods/m8
What "m8" means · taxonomy
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M8
Primary method

Repackaging (quantization)

Applied on top of direct removal inherited from the base model.
Confidence
MEDIUM
Inherited from base model
M1 Direct removal →
Why this label 3 signals
Method inferred from partial signals - repository name, related files, or tag patterns. Producer identity not confirmed; label may sharpen or shift as we gather more evidence.
  • 'abliterated' in name/tags
  • is_gguf=1
  • assume M1 (base ablation) + M8 (GGUF quant) - default when producer unknown
How we label → About M8 →
Refusal direction extraction

No specific extraction method could be identified for this model. The producer either did not document it or used a proprietary pipeline.

What is a refusal direction? →
Downloads · lifetime
2K
763 last 30d - stable
Likes
0
Model age
2mo ago
created 2026-07-20
Downloads over time
Now2.3K→from368↑537%
2691K1.8K2.5K368 on Jul 222.3K on Oct 11JulAugSepOct
Jul 22 → Oct 11 · 52 snapshots · spans 81 days

Genealogy 0 direct forks

Full fork graph →

This model's place in the market. Above: what it was derived from. Below: the tree of everything derived from it.

Carlosian/Qwen3.5-35B-A3B-Abliterated↓ 11,113 this lineage
Carlosian/Qwen3.5-35B-A3B-Abliterated-GGUF↓ 763

Variants by this author 2 formats · 12K downloads combined

The same weights this author released in different packaging. Pick the format that matches your runtime.

Metadata

License
other
Quantizations
Q2_K Q3_K Q4 Q4_K Q5_K Q6_K Q8_0
Tags
gguf quantized abliterated uncensored moe llama.cpp text-generation base_model:Carlosian/Qwen3.5-35B-A3B-Abliterated base_model:quantized:Carlosian/Qwen3.5-35B-A3B-Abliterated license:other endpoints_compatible region:us

Related

Other by Carlosian
Qwen3.5-35B-A3B-Abliterated 11K Gemma-4-12b-it-Abliterated-GGUF 303 Gemma-4-12b-it-Abliterated 30
Total size
205 GB
Files
13
Quantizations
8
Registered
2026-08-22 13:56
Last updated on HF
2026-07-20 12:57
Source huggingface.co/Carlosian/Qwen3.5-35B-A3B-Abliterated-GGUF ↗ Base model Carlosian/Qwen3.5-35B-A3B-Abliterated →

Files by quantization

Q8_0 1 file 34.4 GB
Qwen3.5-35B-A3B-Abliterated.Q8_0.gguf 34.4 GB 0e7a0fbb download
Q6_K 1 file 26.6 GB
Qwen3.5-35B-A3B-Abliterated.Q6_K.gguf 26.6 GB 323fe401 download
Q5_K 2 files 45.4 GB
Qwen3.5-35B-A3B-Abliterated.Q5_K_M.gguf 23.0 GB 32af5ce2 download
Qwen3.5-35B-A3B-Abliterated.Q5_K_S.gguf 22.3 GB bb1c6942 download
Q4_K 2 files 38.2 GB
Qwen3.5-35B-A3B-Abliterated.Q4_K_M.gguf 19.7 GB 6732a9c9 download
Qwen3.5-35B-A3B-Abliterated.Q4_K_S.gguf 18.5 GB 4de365d7 download
Q4 1 file 18.4 GB
Qwen3.5-35B-A3B-Abliterated.Q4_0.gguf 18.4 GB 5dd25c79 download
Q3_K 2 files 29.8 GB
Qwen3.5-35B-A3B-Abliterated.Q3_K_M.gguf 15.6 GB e342f47f download
Qwen3.5-35B-A3B-Abliterated.Q3_K_S.gguf 14.1 GB 76e80614 download
Q2_K 1 file 12.1 GB
Qwen3.5-35B-A3B-Abliterated.Q2_K.gguf 12.1 GB 092e0bbd download
Auxiliary files 3 files 4.18 KB
.gitattributes 2.22 KB 11b1b3e2 download
manifest.jsonl 1.12 KB dec1f688 download
README.md 864 B 32d9c6a8 download

README current version from Hugging Face

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).

README history 3 versions

The author's README evolved over time. Click a version to see its content at that point.

  1. 2026-07-20Upload README.md with huggingface_hubd9232ab864 B
    Loading...
  2. 2026-07-20Add acknowledgments/citations for Nous Research CNA paper + llm-abliteration ...c6186c41.3 KB
    Loading...
  3. 2026-07-20Upload README.md with huggingface_hub5aa1682864 B
    Loading...
Catalog is the map. Apps are the tools.

Run models on your own machine, not in the cloud.

Every model page has an "Open in Abliteration" button that hands the model directly to the first-party desktop client, at the quantization your rig can actually run. No API keys, no subscription, no prompt leakage.

Get the app Browse the catalog
Open in Abliteration