← back to catalog · registered 2026-11-20 22:04

IndrasMirror/Inkling-2-Mini-XQ-Uncensored

IndrasMirror 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/IndrasMirror%2FInkling-2-Mini-XQ-Uncensored"
Response includes
  • classification m8
  • files 2
  • author_summary 11 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
258
Likes
5
Model age
1d ago
created 2026-11-20
Downloads over time
Now 258 → from 0 ↑ 0%
095189284 0 on Nov 20 258 on Nov 22 Nov
Nov 20 → Nov 22 · 3 snapshots · spans 2 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.

Metadata

License
apache-2.0
Languages
en
Tags
gguf speculative-decoding mtp moe inkling inkling-2-mini looped-transformer quantized mixed-precision uncensored abliterated vision

Related

Total size
0 B
Files
2
Quantizations
1
Registered
2026-11-20 22:04
Last updated on HF
2026-11-21 22:35

Files by quantization

Auxiliary files 2 files 7.03 KB
README.md 5.55 KB b81af9c3 download
.gitattributes 1.48 KB a6344aac download

README current version from Hugging Face


license: apache-2.0
license_link: https://www.apache.org/licenses/LICENSE-2.0
base_model:

  • thinkingmachines/Inkling-2-Mini
    base_model_relation: quantized
    tags:
  • gguf
  • moe
  • inkling
  • inkling-2-mini
  • looped-transformer
  • quantized
  • mixed-precision
  • uncensored
  • abliterated
  • xolotl
  • consumer-gpu
    language:
  • en
    pipeline_tag: text-generation

Draft, not released. Sizes, speeds and quality numbers are still being measured. Every TBD below gets a
real number before this card is published.

Inkling-2-Mini · XQ, abliterated

Thinking Machines' Inkling 2 Mini with the refusal
direction edited out of the weights, then requantised with Indra's Mirror's mixed-precision XQ pipeline.
A 26B-parameter looped MoE with about 3B active parameters, 128 routed experts at top-8, and a 1M-token context.

Runs on Xolotl, an engine built for this class of model and machine,
on top of Strata. The forward graph is ported from llama.cpp
(PR #32694 by Pedro Cuenca,
MIT); the engine around it is Xolotl's own.

file size TBD
routed experts TBD
dense backbone TBD
arch / tensors TBD

The model

Inkling 2 Mini is a 24-layer decoder-only transformer with sparse MoE feed-forward blocks. Its middle 12 layers
(layers 6 to 17) run three times with shared weights, so each token gets 48 layer applications out of 24 layers of
weights, and the cache carries 48 slots.

total / active 26B total, about 3B active
loop layers 6 to 17 run 3 passes, 48 cache slots; passes 2 and 3 read the previous pass through per-layer low-rank loop controllers
MoE 128 routed experts, top-8, no shared expert, sigmoid router with a selection bias, SiTU activation
attention sliding window 1024 with a global layer every 6th (5, 11, 17, 23); no RoPE: a learned relative-position bias per head, with log-scaled positions on the global layers
extras short causal convolutions on K, V, the attention output and the FFN output; block attention residuals that mix earlier depths; final logit softcap 30
vocab 200,058
context 1M tokens (the trained key says 1048576)
official precision routed experts NVFP4 on layers 0 to 19, MXFP8 on 20 to 23, everything else BF16

The official checkpoint ships in that mixed precision. This build starts from it rather than from a dequantised
copy, so the native FP4 experts can be carried through at their own precision.

How it was made

  1. Abliteration on the full-precision parts of the official checkpoint. Two candidates are being measured
    against each other (Heretic-style ARA and the classic refusal-direction projection we used for the Qwen3.8
    Flash-Next release); the one that keeps agentic coding quality best on the Gauntlet ships. Refusal gate numbers TBD.
  2. Quantisation with XQ: every tensor gets its own format picked by measured sensitivity for a given
    bits-per-weight budget, with the official NVFP4 and MXFP8 experts used as the source of truth for how much
    precision they can afford to lose. The XQ pipeline itself is private.

Xolotl found and fixed a bug in the llama.cpp loop path along the way: passes 2 and 3 of the loop ran their
experts without the per-expert NVFP4 scale when the GGUF keeps NVFP4 experts. The upstream converter dequantises,
so upstream never meets that case. It is fixed in Xolotl's build.

Quality

Measured against the parent, which is the official checkpoint converted exactly (NVFP4 and MXFP8 kept) and run on
the same engine, hardware and settings.

parent this (XQ)
Gauntlet v3-small, solved TBD TBD
Gauntlet v3-small, score (of 6) TBD TBD
held-out top-1 agreement n/a TBD
held-out KL n/a TBD
refusal gate, harmful prompts refused TBD TBD
refusal gate, harmless prompts refused TBD TBD

The Gauntlet is Xolotl's agentic coding set: hard tasks run over multiple turns with tools in a sandbox, hidden
tests graded after every turn, thinking on, run at the model's recommended sampling over several seeds.

Speed

TBD. The engine is still being written. Numbers will be measured on an RTX 4090 through the real server and
posted here.

Files

file size what
Inkling-2-Mini-XQ-Uncensored.gguf TBD the model
mmproj-Inkling-2-Mini-XQ.gguf TBD planned: the official vision projector, unchanged, for images (text first)

Quick start

Xolotl's xolotl-inkling engine runs any Inkling-2-Mini GGUF: the upstream converter's, llama.cpp's quants, or
this file.

git clone https://github.com/Indras-Mirror/Xolotl.git xolotl && cd xolotl
# build per docs/INSTALL.md, then serve with the Inkling config

Credits

The model is Thinking Machines Lab's, released with open weights under Apache 2.0.
The Inkling 2 forward graph and the GGUF converter come from llama.cpp PR #32694 by Pedro Cuenca (MIT), which
extends the earlier Inkling 2 work in llama.cpp and builds on ggml and llama.cpp by Georgi Gerganov and the
llama.cpp contributors. Xolotl itself is built on Strata by Niko1221.

License

Apache 2.0, the same as the official model. The official card
says, in its General Information section: "License: Apache 2.0", with the link to
LICENSE.

README history 9 versions

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

  1. 2026-11-21 Card: Unbound release (22 Nov), vision in-engine + vision bench, new speed, q... a412495 13.4 KB
    Loading...
  2. 2026-11-21 Card: 22 Nov speeds (decode 113 / DSpark 136 / prefill 4,190 tok/s at 32K, Xo... 629e214 9.8 KB
    Loading...
  3. 2026-11-21 Card: 5.4B active per token (3.1B distinct weights), not ~3B e2a54ac 9.2 KB
    Loading...
  4. 2026-11-21 Card: decode 93 tok/s with Xolotl 58ff5ddbb, quick task screen vs parents, Ga... 4583361 9.1 KB
    Loading...
  5. 2026-11-21 Card: files up and verified 5fd210b 8.2 KB
    Loading...
  6. 2026-11-21 Card: quality + refusal + speed numbers, upload in progress, Gauntlet running bcd37e2 8.2 KB
    Loading...
  7. 2026-11-21 Card: 14 GB picked, quant finishing, spec decode (DSpark/MTP) + quantised KV ... 36e42e5 7.6 KB
    Loading...
  8. 2026-11-21 Card: status + projected upload timeline (in the works, a few hours away) 2c1b25e 6.9 KB
    Loading...
  9. 2026-11-20 Card in prep: Inkling-2-Mini XQ (abliterated), numbers TBD cb6395a 5.5 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