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

scottyjmp5/Legal-Qwen3.6-27B-Abliterated-FP8

scottyjmp5 Qwen 24B multimodal second-order
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/scottyjmp5%2FLegal-Qwen3.6-27B-Abliterated-FP8"
Response includes
  • classification m1
  • files 13
  • hub_downloads_all_time 37
  • author_summary 5 models
  • readme_text full
Try next
GET/models?author=scottyjmp5
All 5 models by scottyjmp5
 GET/models?family=qwen&method=m1
Sibling qwen models · same method
 GET/methods/m1
What "m1" means · taxonomy
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)
How we label → About M1 →
Refusal direction extracted via
Extraction technique

Difference-of-means

FromArditi et al. (2024) ↗
Confidence
MEDIUM
Why we say so
primary_method=M1; difference-of-means is the reference extraction for M1/M3 (Arditi 2024)
What is a refusal direction? → Read the paper ↗
Downloads · lifetime
37
16 last 30d - stable
Likes
0
Model age
2mo ago
created 2026-07-16

Training datasets

Corpora the author lists in the model card. Datasets tracked in our /datasets catalog carry a category badge linking to the workflow stage. Others open on Hugging Face.

scottyjmp5/courtlistener-legal-corpus
Downloads over time
Now43→from9↑378%
72033469 on Jul 1543 on Oct 12JulAugSepOct
Jul 15 → Oct 12 · 54 snapshots · spans 89 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.

scottyjmp5/Legal-Qwen3.6-27B-Abliterated↓ 12 this lineage
scottyjmp5/Legal-Qwen3.6-27B-Abliterated-FP8↓ 16

Variants by this author 3 formats · 108 downloads combined

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

Metadata

License
apache-2.0
Languages
en
Tags
safetensors qwen3_5 legal caselaw abliterated vision tool-calling fp8 compressed-tensors vllm image-text-to-text conversational

Related

Other by scottyjmp5
Legal-Qwen3.6-27B-Abliterated-GGUF 80 Legal-Qwen3.5-9B-Abliterated-GGUF 74 Legal-Qwen3.5-9B-Abliterated 16 Legal-Qwen3.6-27B-Abliterated 12
Same base model
scottyjmp5/Legal-Qwen3.6-27B-Abliterated-GGUF 80
Total size
28.3 GB
Files
13
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2026-07-16 17:59
Source huggingface.co/scottyjmp5/Legal-Qwen3.6-27B-Abliterated-FP8 ↗ Base model scottyjmp5/Legal-Qwen3.6-27B-Abliterated →

Files by quantization

Auxiliary files 13 files 28.3 GB
model.safetensors 28.3 GB c5dbf8cb download
tokenizer.json 19.1 MB 87a7830d download
vocab.json 6.41 MB 0aa0ce06 download
merges.txt 3.20 MB a494e019 download
config.json 14.8 KB e81f28a5 download
chat_template.jinja 7.58 KB a8755d82 download
.gitattributes 1.53 KB 52373fe2 download
README.md 1.45 KB 44e69288 download
tokenizer_config.json 1.17 KB 4d9ac0cf download
preprocessor_config.json 390 B 2ea84a43 download
video_preprocessor_config.json 385 B 3ba673a5 download
generation_config.json 214 B 8a2e2eff download
recipe.yaml 207 B 6dd5ff48 download

README current version from Hugging Face

license: apache-2.0
base_model: scottyjmp5/Legal-Qwen3.6-27B-Abliterated
datasets:

  • scottyjmp5/courtlistener-legal-corpus
    language:
  • en
    pipeline_tag: image-text-to-text
    tags:
  • legal
  • caselaw
  • abliterated
  • vision
  • tool-calling
  • fp8
  • compressed-tensors
  • vllm

Legal-Qwen3.6-27B-Abliterated-FP8

FP8 W8A8 (dynamic per-token activation) quantization of
Legal-Qwen3.6-27B-Abliterated,
produced with llm-compressor.

  • Text Linear layers are FP8; the vision tower, embeddings, and lm_head are kept full precision,
    so vision, tool calling, and thinking mode are unaffected.
  • 29 GB (vs 52 GB bf16). Serves on a single 40GB+ GPU with vLLM (compressed-tensors is
    detected automatically). Fits 2x24GB with tensor parallelism.
  • FP8 W8A8 uses precompiled CUTLASS kernels in vLLM: no custom toolchain needed.
vllm serve scottyjmp5/Legal-Qwen3.6-27B-Abliterated-FP8 \
  --trust-remote-code --max-model-len 8192

Tip observed in testing: FP8's speed advantage over bf16 appears when CUDA graphs are enabled
(the vLLM default). With enforce_eager it can be slightly slower than bf16; with graphs it was
1.67x faster in our single-stream tests.

See the main model card for
training details, the retrieval (RAG) recommendation, and warnings (abliterated base; not legal
advice).

README history 1 version

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

  1. 2026-07-16Upload README.md with huggingface_hub680a68d1.4 KB
    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