← back to catalog · registered 2026-11-09 18:03

mradermacher/Terminal-RSI-27B-Unlocked-Uncensored-Heretic-GGUF

mradermacher 27B GGUF second-order
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/mradermacher%2FTerminal-RSI-27B-Unlocked-Uncensored-Heretic-GGUF"
Response includes
  • classification m3
  • files 15
  • author_summary 3529 models
  • readme_text full
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M3
Primary method

Layer-wise ablation

Applied on top of direct removal inherited from the base model.
Confidence
HIGH
Inherited from base model
Why this label 2 signals
Producer identity confirmed by naming conventions, tags or the model card. This label is very unlikely to change.
  • 'heretic' in model name (Heretic-produced)
  • Heretic uses layer-wise optimization (M3) with underlying direction removal (M1)
Refusal direction extracted via
Extraction technique

Difference-of-means

Confidence
HIGH
Why we say so
name contains 'heretic'; Heretic default extraction is difference-of-means (Arditi 2024)
Downloads · 30-day
345
Likes
0
Model age
1d ago
created 2026-11-09
Downloads over time
Now0→from0↑0%
00110 on Nov 90 on Nov 10Nov
Nov 9 → Nov 10 · 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.

Variants by this author 2 formats · 529 downloads combined

The same weights this author released in different packaging. Pick the format that matches your runtime.

Metadata

License
apache-2.0
Languages
en zh
Quantizations
IQ4 Q2_K Q3_K Q4_K Q5_K Q6_K Q8_0
Tags
transformers gguf terminal-rsi terminal-agent reinforcement-learning recursive-self-improvement code long-context qwen3_5 arxiv:2610.22192 heretic uncensored

Related

Total size
174 GB
Files
15
Quantizations
9
Registered
2026-11-09 18:03
Last updated on HF
2026-11-09 18:35

Files by quantization

Q8_0 2 files 27.2 GB
Terminal-RSI-27B-Unlocked-Uncensored-Heretic.Q8_0.gguf 26.6 GB 25028fcf download
Terminal-RSI-27B-Unlocked-Uncensored-Heretic.mmproj-Q8_0.gguf 600 MB 3b558a8e download
Q6_K 1 file 20.6 GB
Terminal-RSI-27B-Unlocked-Uncensored-Heretic.Q6_K.gguf 20.6 GB 133fafd3 download
Q5_K 2 files 35.3 GB
Terminal-RSI-27B-Unlocked-Uncensored-Heretic.Q5_K_M.gguf 17.9 GB aa18cc25 download
Terminal-RSI-27B-Unlocked-Uncensored-Heretic.Q5_K_S.gguf 17.4 GB 8df7a244 download
Q4_K 2 files 29.9 GB
Terminal-RSI-27B-Unlocked-Uncensored-Heretic.Q4_K_M.gguf 15.4 GB c27e902e download
Terminal-RSI-27B-Unlocked-Uncensored-Heretic.Q4_K_S.gguf 14.5 GB ea588b2e download
IQ4 1 file 14.2 GB
Terminal-RSI-27B-Unlocked-Uncensored-Heretic.IQ4_XS.gguf 14.2 GB 3279a0e9 download
Q3_K 3 files 37.0 GB
Terminal-RSI-27B-Unlocked-Uncensored-Heretic.Q3_K_L.gguf 13.4 GB 17363575 download
Terminal-RSI-27B-Unlocked-Uncensored-Heretic.Q3_K_M.gguf 12.4 GB 1fc79f63 download
Terminal-RSI-27B-Unlocked-Uncensored-Heretic.Q3_K_S.gguf 11.2 GB 032389e4 download
Q2_K 1 file 9.98 GB
Terminal-RSI-27B-Unlocked-Uncensored-Heretic.Q2_K.gguf 9.98 GB 1ae23063 download
F16 1 file 885 MB
Terminal-RSI-27B-Unlocked-Uncensored-Heretic.mmproj-f16.gguf 885 MB b8a1cbd9 download
Auxiliary files 2 files 7.42 KB
README.md 4.75 KB d089b870 download
.gitattributes 2.67 KB 7e472957 download

README current version from Hugging Face


base_model: SolsticeAI/Terminal-RSI-27B-Unlocked-Uncensored-Heretic
language:

  • en
  • zh
    library_name: transformers
    license: apache-2.0
    mradermacher:
    readme_rev: 1
    quantized_by: mradermacher
    tags:
  • terminal-rsi
  • terminal-agent
  • reinforcement-learning
  • recursive-self-improvement
  • code
  • long-context
  • qwen3_5
  • arxiv:2610.22192
  • heretic
  • uncensored
  • decensored
  • abliterated
  • reproducible

About

static quants of https://huggingface.co/SolsticeAI/Terminal-RSI-27B-Unlocked-Uncensored-Heretic

For a convenient overview and download list, visit our model page for this model.

weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion.

Usage

If you are unsure how to use GGUF files, refer to one of TheBloke's
READMEs
for
more details, including on how to concatenate multi-part files.

Provided Quants

(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)

Link Type Size/GB Notes
GGUF mmproj-Q8_0 0.7 multi-modal supplement
GGUF mmproj-f16 1.0 multi-modal supplement
GGUF Q2_K 10.8
GGUF Q3_K_S 12.2
GGUF Q3_K_M 13.4 lower quality
GGUF Q3_K_L 14.4
GGUF IQ4_XS 15.3
GGUF Q4_K_S 15.7 fast, recommended
GGUF Q4_K_M 16.6 fast, recommended
GGUF Q5_K_S 18.8
GGUF Q5_K_M 19.3
GGUF Q6_K 22.2 very good quality
GGUF Q8_0 28.7 fast, best quality

Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):

image.png

And here are Artefact2's thoughts on the matter:
https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9

FAQ / Model Request

See https://huggingface.co/mradermacher/model_requests for some answers to
questions you might have and/or if you want some other model quantized.

Thanks

I thank my company, nethype GmbH, for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time.

README history 4 versions

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

  1. 2026-11-09auto-patch README.md99380214.7 KB
    Loading...
  2. 2026-11-09auto-patch README.md13ea1484.8 KB
    Loading...
  3. 2026-11-09auto-patch README.mdf8989ab4.6 KB
    Loading...
  4. 2026-11-09uploaded from rich1d59f4e6398 B
    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