← back to catalog · registered 2026-11-21 17:04

Kujira/Inkling-2-Mini-CHiPS-Abliterated-GGUF

Kujira GGUF MoE
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/Kujira%2FInkling-2-Mini-CHiPS-Abliterated-GGUF"
Response includes
  • classification m8
  • files 4
  • author_summary 8 models
  • readme_text full
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M8
Primary method

Repackaging (quantization)

Applied on top of direct removal inherited from the base model.
Confidence
MEDIUM
Inherited from base model
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.

What is a refusal direction? →
Downloads · 30-day
0
Likes
0
Model age
today
created 2026-11-21
Downloads over time
Now 0 → from 0 ↑ 0%
0011 0 on Nov 21 0 on Nov 22 Nov
Nov 21 → Nov 22 · 2 snapshots · spans 1 day

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
Quantizations
IQ2
Tags
gguf llama.cpp inkling2_loop moe abliterated decensored chips text-generation base_model:unsloth/Inkling-2-Mini-GGUF base_model:finetune:unsloth/Inkling-2-Mini-GGUF license:apache-2.0 endpoints_compatible

Related

Total size
8.38 GB
Files
4
Quantizations
2
Registered
2026-11-21 17:04
Last updated on HF
2026-11-22 04:18

Files by quantization

IQ2 1 file 8.38 GB
Inkling-2-Mini-CHiPS-Abliterated-UD-IQ2_XXS.gguf 8.38 GB c007a6e9 download
Auxiliary files 3 files 19.1 KB
LICENSE 11.1 KB d6456956 download
README.md 6.46 KB 206bee0f download
.gitattributes 1.57 KB 7d0f8078 download

README current version from Hugging Face


license: apache-2.0
library_name: gguf
pipeline_tag: text-generation
base_model: unsloth/Inkling-2-Mini-GGUF
base_model_relation: finetune
tags:

  • gguf
  • llama.cpp
  • inkling2_loop
  • moe
  • abliterated
  • decensored
  • chips

Inkling 2 Mini · CHiPS-Abliterated (Preview)

A modified version of Unsloth's UD-IQ2_XXS file from Inkling-2-Mini-GGUF, edited to reduce refusals.

Not an official Thinking Machines or Unsloth release. Thinking Machines Lab and Unsloth did not make it and do not endorse it.

Preview. This is an early release. Only the UD-IQ2_XXS file has been checked, and only to some extent, by the author using it by hand. No systematic evaluation has been run yet, so how far refusals are reduced, and what the edit costs in capability, have not been measured. Results will be added to this card later.

  • One file for now: UD-IQ2_XXS. Other quantization sizes will be added over time.
  • Small edit: 6 of 744 tensors are rewritten. All other tensors are byte-identical to the original file, and the metadata is unchanged.
  • Method: the edit was made with CHiPS (see below). The recipe is not published.
  • Runtime: needs mainline llama.cpp with #32704 (see Usage).

What changed

Original This model
Size 8.49 GB 9.00 GB (+6.0%)
Tensors 744 744, of which 6 are rewritten
Attention output, layers 9, 11 and 17 Q8_0 Q8_0 (requantized)
Expert down projections (all 128 experts), layers 11, 17 and 19 NVFP4 Q8_0
All other tensors, including the router byte-identical
Metadata unchanged

The three expert tensors are stored as Q8_0 rather than requantized to 4-bit NVFP4, so the edit is kept at 8-bit precision. This is where the extra 0.51 GB comes from.

Layers 6 to 17 form the looped block that runs three times per token, so the edits in layers 9, 11 and 17 apply on every pass. The edit in layer 19 applies once.

About CHiPS

CHiPS (Causal Head-isolated Projection Steering) reduces one behavior without training. It picks model components by their causal effect on that behavior and reduces the part of their output that lies along one direction. The rest of the model is left untouched. This article explains the method and its results on other models.

In the article, CHiPS edits a few attention heads. On this looped mixture-of-experts model the edit is applied to whole layers instead: the attention output of three layers and the expert down projections of three layers. The recipe is not published.

Files

File Size SHA-256
Inkling-2-Mini-CHiPS-Abliterated-UD-IQ2_XXS.gguf 9.00 GB c007a6e9334f07737a4d4c79ae5d5e62299d2321542f9e3c1b0a69f317e3db74

The original file is Unsloth's Mainline_Support/Inkling-2-Mini-UD-IQ2_XXS.gguf_file (SHA-256 2f953a44281cf861b19ccfdb2ce65f7648e1e92bda4af3729893604fd907c544), in the inkling2_loop layout that mainline llama.cpp reads. This file keeps that layout and uses the normal .gguf extension, so it does not need renaming. LICENSE holds the Apache License 2.0 (see below).

No vision projector is included, and images were not tested with this file.

More quantization sizes will be added over time. The edit was tuned on UD-IQ2_XXS, and other sizes may behave somewhat differently. This card will be updated as files are added.

Usage

hf download Kujira/Inkling-2-Mini-CHiPS-Abliterated-GGUF Inkling-2-Mini-CHiPS-Abliterated-UD-IQ2_XXS.gguf --local-dir .

llama-server -m Inkling-2-Mini-CHiPS-Abliterated-UD-IQ2_XXS.gguf -ngl 99 --jinja -c 32768 \
  --temp 1.0 --top-p 1.0 --top-k 0 --min-p 0.0

Use mainline llama.cpp with #32704, merged on 2026-11-21. Release b12608 and earlier do not include it, so use a later release or build from master. Without the fix, the second and third passes through the looped layers lose their expert scales and the output is gibberish.

Unsloth Studio, Unsloth Desktop and Unsloth's llama.cpp prebuilts are made for the root files of the original repository, which use a different layout. This file was not tried with them.

The sampling settings above are the ones Unsloth recommends for the original model: temperature 1.0 with no truncation. The weights take about 9 GB of GPU or system memory, plus the context cache, so set -c to fit your memory.

Evaluation

Not yet. So far the UD-IQ2_XXS file has only been checked by the author in hand-run chats. Measured results, compared with the original file, will be added here later.

Limitations

  • Nothing has been measured yet. Refusal rates, capability and perplexity have not been compared with the original file.
  • Only UD-IQ2_XXS has been checked, and only by hand.
  • Images, long contexts, tool calling and speculative decoding (including Unsloth's DSpark drafter) were not tested.
  • The original model's limitations still apply. For example, it can get stuck in long reasoning loops, so set limits on output tokens. See the original model card.

Intended use

This model follows many requests that the original model refuses, and it can produce harmful, offensive or inaccurate content. It is meant for research and for users who understand this. You are responsible for how you use it, including compliance with applicable laws and the license below. Add your own safeguards before using it in anything that serves other people.

License

Same license as the original model: the Apache License 2.0. Thinking Machines also publishes a Model Acceptable Use Policy for the original model.

Derivative of Inkling 2 Mini by Thinking Machines Lab, Inc., licensed under the Apache License 2.0. Changes in this repository: the six tensors listed in What changed were rewritten.

Credits

README history 5 versions

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

  1. 2026-11-22 Card: add the 4,096-token evaluation fa4aa63 12.9 KB
    Loading...
  2. 2026-11-21 Card: UD-IQ2_XXS v2 and its refusal evaluation d30cd1e 11.9 KB
    Loading...
  3. 2026-11-21 Add UD-Q2_K_XL and UD-Q3_K_XL to the card 4e87475 11.1 KB
    Loading...
  4. 2026-11-21 Add refusal evaluation on 312 harmful requests 4a4f7d2 9.7 KB
    Loading...
  5. 2026-11-21 Add Inkling 2 Mini CHiPS-Abliterated UD-IQ2_XXS (preview) ade4db0 6.5 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.

Open in Abliteration