← back to catalog · registered 2026-09-19 18:56

shunya1810/huihui-ai-Huihui-Qwen3.8-27B-abliterated-MTPLX

curl -H "Authorization: Bearer $ABL_KEY" \
     "https://abliteration.org/api/v1/models/shunya1810%2Fhuihui-ai-Huihui-Qwen3.8-27B-abliterated-MTPLX"
Response includes
  • classification m1
  • files 17
  • author_summary 1 models
  • readme_text full
10 credits · hourly refresh · ~4 KB payload Get an API key →
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
0
Model age
today
created 2026-09-19

Metadata

Tags
safetensors qwen3_5 4-bit region:us
Total size
15.7 GB
Files
17
Quantizations
1
Registered
2026-09-19 18:56
Last updated on HF
2026-09-19 18:05

Files by quantization

Auxiliary files 17 files 15.8 GB
model-00002-of-00003.safetensors 4.99 GB 0cece59a download
model-00001-of-00003.safetensors 4.96 GB 75084e67 download
model-00003-of-00003.safetensors 4.14 GB ff8d60ab download
model-vision.safetensors 879 MB 964bef26 download
mtp.safetensors 810 MB ed8e6109 download
tokenizer.json 26.8 MB 697dcad3 download
model.safetensors.index.json 202 KB c6b399a4 download
chat_template.jinja 8.74 KB c0c686f9 download
config.json 4.36 KB 92be90e6 download
mtplx_runtime.json 3.95 KB 68456475 download
.gitattributes 1.53 KB 52373fe2 download
tokenizer_config.json 1.13 KB 8d610519 download
README.md 643 B 2dc84aca download
preprocessor_config.json 390 B 2ea84a43 download
video_preprocessor_config.json 385 B 3ba673a5 download
processor_config.json 367 B ced889f7 download
generation_config.json 202 B 023756cf download

README current version from Hugging Face

huihui-ai-Huihui-Qwen3.8-27B-abliterated-MTPLX

MTPLX-branded multi-token-prediction model for Apple Silicon (MLX).
Forged with MTPLX Forge from
huihui-ai/Huihui-Qwen3.8-27B-abliterated.

Verification

  • Best depth: D2
  • Multiplier vs autoregressive baseline: 1.59×
  • Verified on: Apple M1 Max
  • Sampler: temperature 0.6 · top_p 0.95 · top_k 20

See mtplx_runtime.json for the full verification record.

Usage

# MTPLX picks this model up automatically when downloaded:
mtplx pull <owner>/huihui-ai-Huihui-Qwen3.8-27B-abliterated-MTPLX
mtplx start chat

License

See LICENSE.

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.