← back to catalog · registered 2026-08-24 21:02

jlucasvt/Jiunsong-SuperQwen3.8-27b-abliterated-MTPLX

Name: jlucasvt/Jiunsong-SuperQwen3.8-27b-abliterated-MTPLX
Author: jlucasvt

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/jlucasvt%2FJiunsong-SuperQwen3.8-27b-abliterated-MTPLX"

Response includes

classification m1
files 17
hub_downloads_all_time 58
author_summary 1 models
readme_text full

10 credits · hourly refresh · ~4 KB payload Get an API key →

Abliteration classifier · v1.0.0

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

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)

Downloads · lifetime

11 last 30d - stable

Likes

Model age

6w ago

created 2026-08-24

Downloads over time

Aug 26 → Oct 12 · 48 snapshots · spans 47 days

Metadata

Files by quantization

Auxiliary files 17 files 15.8 GB

model-00002-of-00003.safetensors	4.99 GB	90ae317b	download
model-00001-of-00003.safetensors	4.96 GB	0e9a5a09	download
model-00003-of-00003.safetensors	4.14 GB	01822200	download
model-vision.safetensors	879 MB	964bef26	download
mtp.safetensors	810 MB	4468f396	download
tokenizer.json	19.1 MB	06b95093	download
model.safetensors.index.json	202 KB	c6b399a4	download
chat_template.jinja	8.81 KB	1a8a2a3d	download
config.json	4.43 KB	08072c81	download
mtplx_runtime.json	4.24 KB	30db2251	download
.gitattributes	1.53 KB	52373fe2	download
tokenizer_config.json	1.13 KB	8d610519	download
README.md	634 B	53cc9543	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

Jiunsong-SuperQwen3.8-27b-abliterated-MTPLX

MTPLX-branded multi-token-prediction model for Apple Silicon (MLX).
Forged with MTPLX Forge from
Jiunsong/SuperQwen3.8-27b-abliterated.

Verification

Best depth: D3
Multiplier vs autoregressive baseline: 2.43×
Verified on: Apple M5 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>/Jiunsong-SuperQwen3.8-27b-abliterated-MTPLX
mtplx start chat

License

See LICENSE.

README history 4 versions

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

2026-08-24Update MTPLX Forge README163517e634 B
Loading...
2026-08-24Publish MTPLX forged model5a7697c81 B
Loading...
2026-08-24Update MTPLX Forge README8e2367d634 B
Loading...
2026-08-24Publish MTPLX forged modela6e92c281 B
Loading...

jlucasvt/Jiunsong-SuperQwen3.8-27b-abliterated-MTPLX

The browser can't see your hardware

The Abliteration app is integrated with your machine

And you can chat with any model, right now