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

SC117/Ling-3.0-tiny-abliterated-APEX-GGUF

Name: SC117/Ling-3.0-tiny-abliterated-APEX-GGUF
Author: SC117

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/SC117%2FLing-3.0-tiny-abliterated-APEX-GGUF"

Response includes

classification m8
files 9
hub_downloads_all_time 27,875
author_summary 18 models
readme_text full

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

Abliteration classifier · v1.0.0

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

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.

Downloads · lifetime

28K

9K last 30d - stable

Likes

Model age

8w ago

created 2026-08-13

Downloads over time

Aug 14 → Oct 12 · 50 snapshots · spans 59 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.

inclusionAI/Ling-3.0-tiny this lineage

SC117/Ling-3.0-tiny-abliterated-APEX-GGUF↓ 9,049

Metadata

License

mit

Quantizations

BF16

Files by quantization

BF16 1 file 14.7 GB

Ling-3.0-tiny-abliterated-bf16.gguf

14.7 GB

8c2ea2ea

download

Auxiliary files 8 files 17.8 GB

Ling-3.0-tiny-abliterated-APEX-I-Balanced.gguf	5.55 GB	d93bf9bf	download
Ling-3.0-tiny-abliterated-APEX-I-Quality.gguf	5.37 GB	946e158b	download
Ling-3.0-tiny-abliterated-APEX-I-Compact.gguf	3.71 GB	f661876a	download
Ling-3.0-tiny-abliterated-APEX-Mini.gguf	3.17 GB	6d729f13	download
Ling-3.0-tiny-abliterated-imatrix.dat	42.0 MB	8a7e83e3	download
README.md	15.1 KB	bf7f7d19	download
README_zh.md	14.9 KB	929206bf	download
.gitattributes	1.94 KB	9ec26e3d	download

README current version from Hugging Face

library_name: llama.cpp
license: mit
license_link: https://huggingface.co/inclusionAI/Ling-3.0-tiny/blob/main/LICENSE
pipeline_tag: text-generation
tags:

bailing-moe
ling
abliterated
uncensored
decensored
apex
quantization
imatrix
gguf
base_model:
inclusionAI/Ling-3.0-tiny

APEX Abliterated 7.9B MoE

Ling-3.0-tiny

English | 📖 中文文档

Abliterated APEX GGUF quants of inclusionAI/Ling-3.0-tiny — 7.9B total / 1.3B active hybrid-reasoning MoE

🔓 Abliteration

Refusal direction removed with abliterix using LoRA steering search on a bnb-4bit loaded model. Over 130 candidate steering configurations were explored; the Pareto-selected recipe was merged into the BF16 weights.

85% fewer refusals (15/100 vs 98/100 baseline) at 0.0677 KL divergence. Post-abliteration capability spot-checks (math, logic, coding, translation, knowledge) all pass with no degradation observed.

💡 What is APEX?

These GGUF files are quantized using APEX, a novel MoE-aware mixed-precision quantization technique that outperforms standard quantization methods while being significantly smaller.

APEX beats Q8_0 perplexity at half the size — and even beats F16.

APEX classifies every tensor by its role — routed expert, shared expert, or attention — and applies a layer-wise precision gradient, giving the most sensitive edge layers higher precision and compressing the redundant middle layers more aggressively. Ling-3.0-tiny's 128 routed experts (only 8 active per token) make it an ideal candidate.

📦 APEX Quantization Tiers

File	Size	BPW	Best For
`*-APEX-I-Quality.gguf`	5.77 GB	5.84	Highest quality, best accuracy
`*-APEX-I-Balanced.gguf`	5.96 GB	6.03	Best all-rounder, recommended
`*-APEX-I-Compact.gguf`	3.99 GB	4.10	Best quality/size ratio, 8 GB GPUs
`*-APEX-Mini.gguf`	3.41 GB	3.45	Smallest viable, 6 GB GPUs, long context

All tiers quantized from a single BF16 source (15.07 GB) with the same diverse imatrix. Expert tensor layout: edge layers (L0–4, L19–23) keep higher precision than middle layers (L10–13); shared experts stay at Q8_0; the router is never quantized.

📐 I-Variant: Diverse Imatrix Calibration

All tiers use a diverse calibration dataset spanning chat, code, reasoning, and tool-calling — no Wikipedia (500 chunks). This produces higher accuracy on real-world benchmarks, lower KL divergence, and only a tiny perplexity increase on wikitext.

🧠 Model Details

Architecture	BailingMoeV3 — hybrid KDA/MLA linear-attention MoE
Parameters	7.9B total, 1.3B active per token
Experts	128 routed experts + 1 shared expert, 8 routed active per token
Layers	24 layers, 3:1 KDA–MLA stacking
Context	131,072 tokens native
Reasoning	Native hybrid reasoning (thinking mode on by default)
Abliteration	abliterix LoRA steering (85% fewer refusals, 0.0677 KL)

🚀 Usage

llama.cpp

hf download SC117/Ling-3.0-tiny-abliterated-APEX-GGUF --include "*.gguf" --local-dir ./models ./llama-server -m ./models/Ling-3.0-tiny-abliterated-APEX-I-Balanced.gguf -ngl 99 -c 32768 --flash-attn on --jinja

⚠️ bailingmoe3 architecture support: BailingMoE3 (PR #26608) was merged into llama.cpp master on 2026-08-17 — the first release containing it is b10470. Use llama.cpp b10470 or newer. If you see unknown model architecture: 'bailingmoe3', your build is too old — update and it will load.

Ollama

echo 'FROM ./Ling-3.0-tiny-abliterated-APEX-I-Balanced.gguf' > Modelfile ollama create ling-tiny-abliterated -f Modelfile && ollama run ling-tiny-abliterated

🎛️ Recommended Settings

Mode	Parameters
Thinking (default)	temp=1.0, top_p=0.95, top_k=20
Fast / instruct	temp=0.7, top_p=0.8, top_k=20 (disable thinking via chat template)

Citation

@misc{ling3tiny,
title = {{Ling-3.0-tiny}: A Lightweight Hybrid Reasoning MoE Model},
url = {https://huggingface.co/inclusionAI/Ling-3.0-tiny},
author = {{inclusionAI}},
year = {2026}
}

README history 4 versions

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

2026-10-03Add optional Ko-fi support banner151f49515.5 KB
Loading...
2026-08-19Update bailingmoe3 support note (PR #26608 merged into master, first release ...b923d1615.1 KB
Loading...
2026-08-13Upload folder using huggingface_hubd1d356115 KB
Loading...
2026-08-13Upload folder using huggingface_hubefa24cc15 KB
Loading...

Discussions 2 threads

2026-10-09Quality is better and smaller than balanced?closed2 💬#2
Loading...
2026-08-19error loadingopen2 💬#1
Loading...

Continue on Hugging Face →

SC117/Ling-3.0-tiny-abliterated-APEX-GGUF

The browser can't see your hardware

The Abliteration app is integrated with your machine

And you can chat with any model, right now

Repackaging (quantization)

Genealogy 0 direct forks

Metadata

Related

Files by quantization

README current version from Hugging Face

Ling-3.0-tiny

Links

Citation

README history 4 versions

Discussions 2 threads

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