← back to catalog · registered 2026-11-16 00:03

nazeshinjite/Qwen3.8-Flash-Next-Abliterated-LoRA

nazeshinjite Qwen 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/nazeshinjite%2FQwen3.8-Flash-Next-Abliterated-LoRA"
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
425
Likes
7
Model age
6d ago
created 2026-11-15
Downloads over time
Now 425 → from 0 ↑ 0%
0156312468 0 on Nov 16 425 on Nov 22 Nov
Nov 16 → Nov 22 · 7 snapshots · spans 6 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
other
Quantizations
F32
Tags
llama.cpp gguf lora abliterated uncensored qwen3_8 moe base_model:Qwen/Qwen3.8-Flash-Next base_model:adapter:Qwen/Qwen3.8-Flash-Next license:other region:us

Related

Control vectors

Total size
2.19 MB
Files
3
Quantizations
2
Registered
2026-11-16 00:03
Last updated on HF
2026-11-16 05:36

Files by quantization

F32 1 file 2.19 MB
HUIHUI-V2-Qwen3.8-Flash-Next-LoRA-F32.gguf 2.19 MB 349022ca download
Auxiliary files 2 files 7.50 KB
README.md 5.94 KB 6d2bee45 download
.gitattributes 1.56 KB 95b9868b download

README current version from Hugging Face


license: other
license_name: qwen-community-1.0
base_model:

  • Qwen/Qwen3.8-Flash-Next
    base_model_relation: adapter
    library_name: llama.cpp
    tags:
  • lora
  • gguf
  • llama.cpp
  • abliterated
  • uncensored
  • qwen3_8
  • moe

Qwen3.8-Flash-Next Abliterated LoRA

A 2.3 MB rank-1 LoRA (GGUF, F32) that applies
huihui's v2 abliteration of
Qwen3.8-Flash-Next at runtime, build and tested top of Unsloth (but works on other quants/fine-tunes too).
Instead of downloading a second copy of the model, load one extra file and turn it on or off per request.

Download
huihui v2 UD-Q5_K_XL (full model) 158.3 GB
This LoRA (use the model you already have) 2.3 MB

Results

LoRA applied to Unsloth UD-Q5_K_XL, measured against against huihui's v2 UD-Q5_K_XL. In all
arms the PLE n-gram table was BF16; no PLE tensors are edited.

Refusals (count of 100). Judged by an LLM judge (the base model, greedy) that agreed with 18/20 hand labels.
Sampled at the model-card defaults (temperature 1.0); thinking prompts run at effort xhigh; same prompts and
seeds for every model.

Prompt set Base Q5 + this LoRA huihui v2 Q5 LoRA vs huihui (McNemar p)
harmful_behaviors, instruct 99 14 14 1.00
JailbreakBench harmful, instruct 93 15 11 0.39
JailbreakBench harmful, thinking 93 3 5 0.69
JailbreakBench benign (over-refusal) 18 0 1 1.00

No set shows a significant difference between the LoRA and huihui's v2 Q5.

KL divergence from the base Q5 (llama-perplexity, 64 × 512 tokens):

Corpus + this LoRA huihui v2 Q5
WikiText-2 (KLD / same top token) 0.040 / 93.7% 0.040 / 93.8%
Base model's own chat answers 0.038 / 93.7% 0.044 / 93.2%
Base model's refusal text 0.388 / 79.1% 0.389 / 79.0%
  • WikiText-2 perplexity is unchanged (Δln PPL +0.0005).
  • The edit concentrates on refusal text, about 10× more than on ordinary chat.
  • LoRA vs huihui v2 Q5: KLD 0.016 on WikiText-2. Re-quantizing this exact F32 edit to Q8_0 costs 0.014, so the gap is rounding noise.

Side effects:

  • Tool calling is unchanged: a 35-case suite gives 29/29 valid calls, the same as base.
  • Decode speed is within noise of base.
  • Extra memory is < 0.1 GiB.

Usage (llama.cpp)

Any llama.cpp build that runs Qwen3.8-Flash-Next (qwen4exp). It was evaluated on v0.8.0 and load-tested on
v1.0.0.

Always on (behaves identically to huihui's v2 model):

llama-server -m Qwen3.8-Flash-Next-UD-Q5_K_XL-00001-of-00006.gguf \
  --lora HUIHUI-V2-Qwen3.8-Flash-Next-LoRA-F32.gguf -fa on --jinja

Per request: An abliterated model is abliterated for every prompt, so even ordinary answers drift
from the original (KLD 0.040 above). With LoRA, you can keep the stock model behavior and apply the
abliteration only to the prompts it refuses:

llama-server -m Qwen3.8-Flash-Next-UD-Q5_K_XL-00001-of-00006.gguf \
  --lora HUIHUI-V2-Qwen3.8-Flash-Next-LoRA-F32.gguf --lora-init-without-apply -fa on --jinja

--lora-init-without-apply loads the adapter at scale 0, so requests get the stock model by default. Add a lora
field to the request body to enable it:

curl http://127.0.0.1:8080/v1/chat/completions -H 'Content-Type: application/json' -d '{
  "messages": [{"role": "user", "content": "..."}],
  "lora": [{"id": 0, "scale": 1.0}]
}'
  • Retry on refusal: send the prompt as usual; if the answer is a refusal, resend the same request with
    "lora": [{"id": 0, "scale": 1.0}]. Every other prompt keeps exact stock-model outputs. This can be automated with a simple pi extension.
  • Cost of switching: when a request's adapter setting differs from the previous one, llama-server discards
    that slot's cached prompt and processes it again.
  • GET /lora-adapters lists the loaded adapter and its id.

What it is

huihui's v2 edit is a single direction, removed from 96 residual writers in layers 0–47: ssm_out ×36,
attn_output ×12 and ffn_down_shexp ×48. It's applied at a uniform strength of 1.78, and routed experts are
untouched.

This LoRA is the rank-1 form of that edit, extracted against Unsloth's UD-Q5_K_XL:

  • Every module's direction matches huihui's at |cos| ≥ 0.9999.
  • The rank-1 part holds 93–95% of each weight delta; the remainder is Q8_0 rounding noise.

Why huihui's abliteration

orcarouter's Uncensored model removes basically the same
refusal direction, but from every writer, including all routed experts and the embeddings. huihui's edit is
narrower. We compared the two on the same Aider Polyglot coding benchmarks:

Pass@2 Median tokens Tokens/solve
Base 90.5% 14.5K 20.9K
huihui 92.9% 16.3K 21.4K
orca 90.5% 22.1K 24.8K
  • orca reasons ~35% longer than huihui (+52% vs base) for the same score, and its long generations ran longer
    (90th percentile 42K vs 36K tokens). Over its full run one exercise ran out of context; huihui and base had none.
  • huihui stays close to base on reasoning length (+12% median).

Notes:

  • Built and evaluated on UD-Q5_K_XL. Works on other quants and fine-tunes like Swift 1.5 and ThinkingCap, applied at the same strength (1.775–1.782).
  • Don't stack it on an already-abliterated model.
  • Like any abliteration, this removes refusals. Review outputs, and use it in line with the base model's license and
    your local laws. Not responsible for any issues.

Credits

  • The abliteration direction and strength are huihui-ai's v2 work.
  • Base model Qwen/Qwen3.8-Flash-Next; quantization by
    Unsloth.
  • sha256 of the GGUF: 349022ca699f47205837b45f99e8a372077c0a1428920603d00b3b80bb31ee0f

README history 3 versions

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

  1. 2026-11-16 Update README.md dee8e01 5.9 KB
    Loading...
  2. 2026-11-15 Add the huihui v2 abliteration LoRA (rank-1 F32 GGUF) and model card 1d6e428 5.9 KB
    Loading...
  3. 2026-11-15 initial commit 63afb03 28 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