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

luvette/SenseNova-Loop-9B-Preview-abliterated-GGUF

luvette 9B GGUF
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/luvette%2FSenseNova-Loop-9B-Preview-abliterated-GGUF"
Response includes
  • classification m8
  • files 3
  • author_summary 1 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
674
Likes
2
Model age
4d ago
created 2026-11-17
Downloads over time
Now 674 → from 0 ↑ 0%
0247494741 0 on Nov 17 674 on Nov 22 Nov
Nov 17 → Nov 22 · 6 snapshots · spans 5 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
Tags
gguf sensenova sensenova-loop looped-transformer abliterated uncensored text-generation base_model:AtomicChat/SenseNova-Loop-9B-Preview-GGUF base_model:quantized:AtomicChat/SenseNova-Loop-9B-Preview-GGUF license:apache-2.0 endpoints_compatible region:us
Total size
6.87 GB
Files
3
Quantizations
1
Registered
2026-11-17 21:04
Last updated on HF
2026-11-17 21:29

Files by quantization

Auxiliary files 3 files 6.87 GB
SenseNova-Loop-9B-Preview-Q6_K-abliterated.gguf 6.87 GB 75c5b9c5 download
README.md 3.25 KB 0a5446c1 download
.gitattributes 1.57 KB 2f72bf0d download

README current version from Hugging Face


license: apache-2.0
base_model:

  • sensenova/SenseNova-Loop-9B-Preview
  • AtomicChat/SenseNova-Loop-9B-Preview-GGUF
    base_model_relation: quantized
    pipeline_tag: text-generation
    library_name: gguf
    tags:
  • gguf
  • sensenova
  • sensenova-loop
  • looped-transformer
  • abliterated
  • uncensored

SenseNova-Loop-9B-Preview-abliterated-GGUF

A deeply abliterated (5-pass refusal-direction orthogonalized) version of SenseNova-Loop-9B-Preview-Q6_K.gguf, performed directly on the Q6_K GGUF weights.

Credits

Method (5-Pass Deep Q6_K Abliteration)

Iterative 5-pass refusal-subspace orthogonalization directly on the Q6_K GGUF weights (attn_output.weight, ssm_out.weight, ffn_down.weight), re-extracting per-layer difference-of-means residual vectors (l_out across all 56 expanded layer passes) after each pass:

  1. Pass 1 (Blocks 6-31, alpha = 1.20, 52 tensors): Initial refusal direction removal.
  2. Pass 2 (Blocks 4-31, alpha = 1.25, 56 tensors): Residual refusal removal across the full looped region.
  3. Pass 3 (Blocks 2-31, alpha = 1.30, 60 tensors): Early-layer + residual refusal/caution removal.
  4. Pass 4 (Blocks 2-31, alpha = 1.25, 60 tensors): Deep residual cleanup.
  5. Pass 5 (Blocks 1-31, alpha = 1.25, 62 tensors): Final deep pass eliminating remaining hesitation even inside <think> reasoning traces.

All GGUF metadata, tokenizer, chat template, and F32 mHC Sinkhorn router weights are preserved untouched.

Files

File Quant Size Description
SenseNova-Loop-9B-Preview-Q6_K-abliterated.gguf Q6_K 7.37 GB 5-pass deeply abliterated text-only GGUF

Running

SenseNova-Loop uses a looped Qwen3.5-class backbone (layers 4-27 executed twice = 56 layer computations from 32 stored blocks) with two-stream manifold-constrained hyper-connections (mHC, Sinkhorn routing). You need a llama.cpp build with sensenova_loop + qwen35.num_loops support.

llama-server -m SenseNova-Loop-9B-Preview-Q6_K-abliterated.gguf \
  -ngl 99 -fa on -ctk q8_0 -ctv q8_0 -c 16384 \
  --temp 0.6 --top-p 0.95 --top-k 20

8 GB VRAM Tip (e.g. RTX 3070): Add -ot 'token_embd.weight=CPU' to keep the ~835 MiB embedding table in system RAM so all 56 layer passes, output.weight, and 16K q8_0 KV cache fit 100% in VRAM (~7.17 GB / 8 GB) with CUDA Graphs active (~24.4 t/s generation, ~632 t/s prompt processing on RTX 3070).

Verification

Tested on RTX 3070 (llama-server) across math (17 * 23 = 391), typed Python coding, and unframed sensitive/refusal prompts — direct responses with zero ethical hesitation in <think> traces and full math/coding coherence preserved.

License

Apache License 2.0, inherited from sensenova/SenseNova-Loop-9B-Preview and AtomicChat/SenseNova-Loop-9B-Preview-GGUF.

README history 8 versions

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

  1. 2026-11-17 Upload README.md with huggingface_hub 4d54b69 3.3 KB
    Loading...
  2. 2026-11-17 Upload README.md with huggingface_hub 4cff117 3.4 KB
    Loading...
  3. 2026-11-17 Upload README.md with huggingface_hub 7330bf0 3.2 KB
    Loading...
  4. 2026-11-17 Upload README.md with huggingface_hub 023b9d2 3.1 KB
    Loading...
  5. 2026-11-17 Upload README.md with huggingface_hub 4f2b796 3.1 KB
    Loading...
  6. 2026-11-17 Upload README.md with huggingface_hub e4f637d 3 KB
    Loading...
  7. 2026-11-17 Upload README.md with huggingface_hub d3f089a 500 B
    Loading...
  8. 2026-11-17 Upload README.md with huggingface_hub 7475d2d 411 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