← back to catalog · registered 2026-09-13 16:56

dream-vault-community/Qwen3.5-4B-4bit-Abliterated

dream-vault-community 4B multimodal second-order
Abliteration classifier · v1.0.0
M1
Primary method

Direct removal

No other method signals detected in this model.
Confidence
MEDIUM
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=0 (base model)
  • no specific method indicators - defaulting to M1 (most common)
Refusal direction extracted via
Extraction technique

Difference-of-means

Confidence
MEDIUM
Why we say so
primary_method=M1; difference-of-means is the reference extraction for M1/M3 (Arditi 2024)
Downloads · 30-day
0
Likes
1
Model age
today
created 2026-09-13

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.

Metadata

License
apache-2.0
Tags
mlx safetensors qwen3_5 vision abliterated 4-bit image-text-to-text conversational base_model:mlx-community/Huihui-Qwen3.5-4B-Claude-4.6-Opus-abliterated-4bit base_model:quantized:mlx-community/Huihui-Qwen3.5-4B-Claude-4.6-Opus-abliterated-4bit license:apache-2.0 region:us

Related

Total size
2.83 GB
Files
14
Quantizations
1
Registered
2026-09-13 16:56
Last updated on HF
2026-09-13 16:49

Files by quantization

Auxiliary files 14 files 2.84 GB
model.safetensors 2.83 GB a8b882de download
tokenizer.json 19.1 MB 87a7830d download
model.safetensors.index.json 99.6 KB 40196ba5 download
LICENSE 11.3 KB f938136e download
tokenizer_config.json 8.97 KB 15ac03fe download
chat_template.jinja 7.57 KB a585dec8 download
config.json 3.56 KB 7c152aa7 download
README.md 2.92 KB 0097a1f9 download
.gitattributes 1.53 KB 52373fe2 download
SHA256SUMS 1.43 KB d477caa0 download
PROVENANCE.json 1.35 KB 498c4aff download
processor_config.json 1.27 KB 7ad6acdf download
UPSTREAM_README.md 965 B 8bbe2368 download
preprocessor_config.json 518 B 8055efef download

README current version from Hugging Face


library_name: mlx
license: apache-2.0
pipeline_tag: image-text-to-text
base_model: mlx-community/Huihui-Qwen3.5-4B-Claude-4.6-Opus-abliterated-4bit
base_model_relation: quantized
tags:

  • mlx
  • qwen3_5
  • vision
  • abliterated
  • 4-bit

Qwen3.5-4B-4bit-Abliterated

Standalone MLX 4-bit image-and-text model, repackaged for Dream Vault and mlx-swift-lm compatibility from mlx-community/Huihui-Qwen3.5-4B-Claude-4.6-Opus-abliterated-4bit.

This is the Huihui abliterated derivative of the Jackrong Claude 4.6 Opus reasoning-distilled Qwen3.5 model. These are upstream lineage labels; this release makes no claim of affiliation with Anthropic.

The model already contains its vision encoder. All safetensors are preserved byte for byte. No training or further abliteration was performed. Quantization is 4-bit affine with group size 64, as supplied upstream.

Compatibility changes

Added a flat preprocessor_config.json derived from the existing nested image processor configuration for Swift's Qwen3VL processor. The original processor_config.json and model configuration are preserved. The upstream text-only chat template was replaced with the matching pinned official Qwen3.5 image-aware template, including the tokenizer configuration copy. Image normalization, patch size, temporal patch size, merge size and pixel limits remain those of the source.

Python image inference

python -m mlx_vlm.generate --model dream-vault-community/Qwen3.5-4B-4bit-Abliterated --image /path/to/image.png --prompt "Describe this image." --max-tokens 256 --temperature 0.0

Use an Apple Silicon Mac with MLX and a version of mlx-vlm supporting Qwen3.5. Local release directories can replace the model repository argument. Runtime validation results, when available, are recorded separately; this card does not imply testing of unlisted runtimes or video inference.

Provenance and license

Pinned source revision: a0cd61406062a7bee31fc995a806fdb876f318ed. See PROVENANCE.json, SHA256SUMS and the unchanged UPSTREAM_README.md for source details. The immediate upstream declares Apache-2.0 but does not ship a license file; LICENSE is copied from the corresponding original Qwen3.5 release.

Abliteration is the upstream author's characterization, not a guarantee of any particular behavior. Generated image descriptions can be inaccurate; model quality and safety behavior were not comprehensively benchmarked for this compatibility repackaging.

Validation results

See validation/REPORT.md for runtime versions, synthetic image inference results, and limitations. The public fixture and Swift output are included in validation/. This is a smoke test, not a general image-understanding benchmark.

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 app" button that hands off directly to a local runtime of your choice - Infrahuman, LM Studio, or Ollama. No API keys, no subscription, no prompt leakage.