← back to catalog · registered 2026-11-18 06:04

satellitedown/SenseNova-Loop-9B-abliterated-GGUF

satellitedown 9B 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/satellitedown%2FSenseNova-Loop-9B-abliterated-GGUF"
Response includes
  • classification m8
  • files 6
  • author_summary 5 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
9K
Likes
6
Model age
4d ago
created 2026-11-18
Downloads over time
Now 8.8K → from 0 ↑ 0%
03.2K6.4K9.7K 0 on Nov 18 8.8K on Nov 22 Nov
Nov 18 → Nov 22 · 5 snapshots · spans 4 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.

Variants by this author 2 formats · 9K 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
Q4_K Q6_K
Tags
gguf abliterated uncensored heretic looped-transformer mhc text-generation en zh base_model:satellitedown/SenseNova-Loop-9B-abliterated base_model:quantized:satellitedown/SenseNova-Loop-9B-abliterated license:apache-2.0

Related

Total size
12.1 GB
Files
6
Quantizations
3
Registered
2026-11-18 06:04
Last updated on HF
2026-11-21 21:17

Files by quantization

Q6_K 1 file 6.87 GB
SenseNova-Loop-9B-abliterated-Q6_K.gguf 6.87 GB 956b2bc3 download
Q4_K 1 file 5.25 GB
SenseNova-Loop-9B-abliterated-Q4_K_M.gguf 5.25 GB af9d1ee3 download
Auxiliary files 4 files 18.1 KB
LICENSE 11.1 KB d6456956 download
README.md 4.76 KB a74af36c download
.gitattributes 1.63 KB a9742d90 download
NOTICE 599 B 0c64b240 download

README current version from Hugging Face


license: apache-2.0
base_model: satellitedown/SenseNova-Loop-9B-abliterated
base_model_relation: quantized
language:

  • en
  • zh
    pipeline_tag: text-generation
    tags:
  • gguf
  • abliterated
  • uncensored
  • heretic
  • looped-transformer
  • mhc

SenseNova-Loop-9B-abliterated-GGUF

GGUF builds of satellitedown/SenseNova-Loop-9B-abliterated: SenseNova-Loop-9B with its refusals removed, chosen by whether it carries out harmful requests rather than by whether it refuses them. Text only; the vision tower is not included.

File Size Same top token as full precision Mean KL M4 MacBook Air, 16 GB
SenseNova-Loop-9B-abliterated-Q4_K_M.gguf 5.64 GB 94.1% 0.0333 11.11 tokens/s
SenseNova-Loop-9B-abliterated-Q6_K.gguf 7.38 GB 98.3% 0.0036 8.72 tokens/s

Accuracy is measured against the full-precision abliterated model on 661 token positions. Speed is plain generation in short runs. The Air has no fan: under continuous work the 4-bit file dropped to about 9 tokens/s within minutes and to about 7 after twenty-five.

On a 16 GB Mac use the 4-bit file. With the 6-bit file loaded at a 32K context, the test machine had under 0.1 GB of memory free and was using swap.

These files need a patched llama.cpp

Mainline llama.cpp cannot load this architecture yet, so neither can the apps built on it, such as LM Studio and Ollama. Use the SenseNova Loop fork (https://github.com/GuideboardLabs/llama.cpp-sensenova-loop) at commit a7f77a788893ef2cb17c82b9ac0cb1279bcd0918 with the four patches in patches/ of this repo, which apply to it cleanly (git am):

git clone https://github.com/GuideboardLabs/llama.cpp-sensenova-loop llama.cpp-loop && cd llama.cpp-loop
git checkout a7f77a788893ef2cb17c82b9ac0cb1279bcd0918   # the fork's SenseNova Loop commit, where the patches apply
git am /path/to/patches/*.patch
cmake -B build -DCMAKE_BUILD_TYPE=Release && cmake --build build --target llama-server -j
./build/bin/llama-server -m SenseNova-Loop-9B-abliterated-Q4_K_M.gguf -ngl 99 -c 24576 --jinja -fa on --parallel 1 --cache-ram 0 --ctx-checkpoints 3 --spec-type ngram-simple

What the patches do:

  • Apple GPU kernels for the model's two stream-mixing operations, which otherwise fall back to the CPU twice per looped layer.
  • Router weights kept at 32 bits in the converter. Conversions through a 16-bit intermediate round them.
  • Release checkpoint support in the converter.
  • Prompt reuse across conversations: the server keeps the state after the system prompt and tool definitions, so a new conversation with the same ones does not process them again. On this model that cuts the first request of a new conversation from about 1,330 processed tokens to 80.

--spec-type ngram-simple lets the server draft text it has already seen and check many tokens at once: rewriting a file with one small change ran at 43.11 tokens/s with the 4-bit file, against 11.11 for new text.

--cache-ram 0 --ctx-checkpoints 3 matters on small machines: with the defaults the server grew by 8.4 GB over 138 short requests on the test Mac and was killed.

How the files were made

Converted from the BF16 weights, then llama-quantize with the two small linear-attention gate tensors of every layer (ssm_alpha, ssm_beta) kept at 16 bits, 13 MB in total.

Results of the abliteration

What these files do with harmful requests, answering through llama.cpp, against the original at full precision:

On 83 unseen harmful requests Carries out the request Dodges, answering a harmless question instead Refuses, or gives no answer
Original, full precision 0 3 80
4-bit, thinking on 60 22 1
4-bit, thinking off 50 32 1
6-bit, thinking on 57 24 2
6-bit, thinking off 44 38 1
Full precision, thinking on 58 25 0

Both files carry out more with thinking on, which is the default. Thinking off through the chat template is the weak mode in every build; the full-precision card says why and what to do instead. A request now and then never stops thinking (1 of the 83 with the 4-bit file, 1 with the 6-bit, within 4,000 tokens); those count as refused. Coding-agent tasks passed with the 4-bit file: 10/10 (the original's 4-bit build: 10/10). How the labels were produced, and the limits, are on the full-precision card.

Licence

Apache-2.0, the licence of the original. This is a modified version of sensenova/SenseNova-Loop-9B; see NOTICE. The patches are MIT, like llama.cpp.

README history 7 versions

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

  1. 2026-11-21 Card: patch 0019, the CUDA kernel by Delea; on NVIDIA cards drafting at tempe... 1b4455e 11.5 KB
    Loading...
  2. 2026-11-21 Card: the -hf tags for the upstream-layout files 2644d93 11 KB
    Loading...
  3. 2026-11-21 Add the 4-bit and 6-bit files in the layout of llama.cpp's own SenseNova Loop... c53c3b7 10.8 KB
    Loading...
  4. 2026-11-18 Upload folder using huggingface_hub f50d0b5 9.5 KB
    Loading...
  5. 2026-11-18 Upload folder using huggingface_hub aa85973 7.9 KB
    Loading...
  6. 2026-11-18 Upload folder using huggingface_hub 0a4d265 4.8 KB
    Loading...
  7. 2026-11-18 Upload folder using huggingface_hub 50f5b5e 498 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