← back to catalog · registered 2026-11-22 01:04

Harsha001/Inkling-2-Mini-Uncensored-ROCmFPX

Harsha001 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/Harsha001%2FInkling-2-Mini-Uncensored-ROCmFPX"
Response includes
  • classification m8
  • files 6
  • 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
20
Likes
2
Model age
1d ago
created 2026-11-21

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
Q4 Q6_K Q8_0
Tags
gguf rocmfpx amd vulkan rocm strix-halo quantized moe inkling inkling2 uncensored abliterated

Related

Total size
59.6 GB
Files
6
Quantizations
4
Registered
2026-11-22 01:04
Last updated on HF
2026-11-22 00:05

Files by quantization

Q8_0 1 file 25.1 GB
Inkling-2-Mini-Uncensored-Q8_0_ROCMFPX.gguf 25.1 GB 0f8eafd8 download
Q6_K 1 file 20.1 GB
Inkling-2-Mini-Uncensored-Q6_K_ROCMFPX.gguf 20.1 GB d68a5a6e download
Q4 1 file 14.4 GB
Inkling-2-Mini-Uncensored-Q4_0_ROCMFP4_STRIX_O8.gguf 14.4 GB 5d48e13c download
Auxiliary files 3 files 19.4 KB
LICENSE 11.3 KB f938136e download
README.md 6.17 KB 5ebbc85c download
.gitattributes 1.94 KB 997985de download

README current version from Hugging Face


license: apache-2.0
base_model:

  • thinkingmachines/Inkling-2-Mini
  • AtomicChat/Inkling-2-Mini-Uncensored-GGUF
    base_model_relation: quantized
    pipeline_tag: text-generation
    library_name: gguf
    tags: [gguf, rocmfpx, amd, vulkan, rocm, strix-halo, quantized, moe, inkling, inkling2, uncensored, abliterated]

Inkling 2 Mini Uncensored ROCmFPX (AMD GPUs and Strix Halo)

Update, 21 November 2026: the files in this repository are now the uncensored model. They are built from
Thinking Machines' original weights with AtomicChat's uncensoring edit
merged in, and they replace the earlier censored files. A 6-bit file was added. The repository and the files were
renamed to Inkling-2-Mini-Uncensored (old links redirect here). The model now answers
requests the original refuses. The earlier files are still in this repository's commit history.

Hardware-aware GGUF quants of Inkling 2 Mini by Thinking Machines,
built with the ROCmFPX weight formats for AMD GPUs (Vulkan and ROCm).

Inkling 2 Mini: 26.1B parameters, 24 layers, 128 experts per layer with 8 active per token (about 3.1B active
parameters per layer pass). It is a looped model: layers 6 to 17 run three times per token, so a token passes through
48 layers. Text only here: the vision encoder and the multi-token prediction drafter are not included.

Not an official release. All credit for the model goes to Thinking Machines, and for the uncensoring edit to AtomicChat.

Files

File Size Weights Fits
Inkling-2-Mini-Uncensored-Q8_0_ROCMFPX.gguf 26.9 GB everything 8-bit ROCmFPX (token embedding Q8_0) best quality: Strix Halo, 32 GB AMD GPUs
Inkling-2-Mini-Uncensored-Q6_K_ROCMFPX.gguf 21.6 GB experts 6-bit ROCmFPX, everything else 8-bit ROCmFPX Strix Halo, 24 to 32 GB AMD GPUs
Inkling-2-Mini-Uncensored-Q4_0_ROCMFP4_STRIX_O8.gguf 15.5 GB experts ROCmFP4, everything else 8-bit ROCmFPX smallest: 24 GB AMD GPUs, Strix Halo with room for long context

The names start with a stock type name (Q8_0, Q6_K, Q4_0) only so the Hugging Face file list sorts them by
bit width. The weights are ROCmFPX formats and need the ROCmFPX fork.

The uncensoring edit

AtomicChat's edit is a rank-1 LoRA on the attention output and the routed experts of all 24 layers plus the token
embedding. In each layer it removes that layer's refusal direction. Their measurements: no refusals on their harmful
test prompts in English and Russian (the original refused 91 to 100%), no refusals on XSTest's safe prompts (the
original refused 4%), MMLU 79.15% against 80.65% for the original. See their card for the full table.

Here their adapter (Inkling-2-Mini-Uncensored-LoRA.gguf, revision 40886ab6) is merged at strength 1 into the original
checkpoint in full precision, and that merged model is the reference for the numbers below.

This model will answer requests that the original refuses. You are responsible for how you use it.

Quality

KL divergence against the merged full-precision model, 40 chunks of 512 tokens of English Wikipedia text
(wikitext-2), CPU. Lower is better. "Same top token" is how often the file's most likely next token matches the
reference.

Build Size Perplexity KL to reference Same top token
Merged reference (not published) 50.5 GB 6.775
original model, for comparison (not published) 22.9 GB 6.743
Q8_0_ROCMFPX 26.9 GB 6.758 0.0039 97.4%
Q6_K_ROCMFPX 21.6 GB 6.777 0.0046 96.9%
Q4_0_ROCMFP4_STRIX_O8 15.5 GB 6.799 0.0119 95.2%

The quantization costs the same as in the earlier censored files (Q8 0.0039, 4-bit 0.0120 against their own
reference). The edit itself raises wikitext perplexity by about 0.5% (6.743 to 6.775).

Every file also passed a greedy chat check before upload ("What is the capital of France? Answer in one word." gives
"Paris"), and answered three prompts the original refuses.

Running it

Inkling 2 Mini needs the looped inkling2 graph, which is only in the ROCmFPX fork of llama.cpp (branch
inkling2-mini). These files do not load in upstream llama.cpp, and AtomicChat's files do not load in the fork: the
two use different tensor layouts. Build the fork with Vulkan or ROCm/HIP, then for example:

llama-server -m Inkling-2-Mini-Uncensored-Q4_0_ROCMFP4_STRIX_O8.gguf -ngl 99 -c 16384 --jinja

Known limits of this first version:

  • Only the CPU path has been checked against the original PyTorch model (it matches to about 5e-6 on a small test
    model, and the tokenizer matches exactly). Vulkan and ROCm have not been tried yet. Please report in the Community
    tab whether it runs, how fast, and how the answers look.
  • llama.cpp has no parser for Inkling's message format yet. Answers come back with Inkling's own markers
    (<|content_thinking|>, <|end_message|> and so on): the thinking is not split from the answer and tool calls are
    not parsed. Plain chat works; agent use does not yet.
  • The chat template accepts reasoning_effort as none, minimal, low, medium, high, xhigh or max,
    or as a number from 0 to 0.99 (default 0.9).

How it was made

  • Converted from the original checkpoint. The expert down projections, the attention outputs and the token embedding
    get the LoRA added in F32; the other NVFP4 experts are kept as they are. Then requantized with llama-quantize.
  • ROCmFPX tensor scales on (a power-of-two scale per tensor, stored as .scale), token embedding Q8_0.
  • Importance matrix from a general text mix (prose, code, chat), taken on the original weights (a rank-1 edit
    barely changes it).

Credits and license

Apache-2.0. See LICENSE.

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 Model card: renamed to Inkling 2 Mini Uncensored f2ebf5f 6.2 KB
    Loading...
  2. 2026-11-21 Model card d2e22c3 6 KB
    Loading...
  3. 2026-11-21 Card: stock comparison rows 9890076 4.4 KB
    Loading...
  4. 2026-11-21 Model card and licence 2116290 4 KB
    Loading...
  5. 2026-11-21 Model card and licence bc27072 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.

Open in Abliteration