Get the app
← back to catalog · registered 2026-08-26 04:02

windowsxp811203/Qwen3.8-Flash-Next-Abliterated-NVFP4

windowsxp811203 Qwen 60B
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/windowsxp811203%2FQwen3.8-Flash-Next-Abliterated-NVFP4"
Response includes
  • classification m1
  • files 2
  • hub_downloads_all_time 559
  • author_summary 17 models
  • readme_text full
Try next
GET/models?author=windowsxp811203
All 17 models by windowsxp811203
 GET/models?family=qwen&method=m1
Sibling qwen models · same method
 GET/methods/m1
What "m1" means · taxonomy
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M1
Primary method

Direct removal

No other method signals detected in this model.
Confidence
MEDIUM
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=0 (base model)
  • no specific method indicators - defaulting to M1 (most common)
How we label → About M1 →
Refusal direction extracted via
Extraction technique

Difference-of-means

FromArditi et al. (2024) ↗
Confidence
MEDIUM
Why we say so
primary_method=M1; difference-of-means is the reference extraction for M1/M3 (Arditi 2024)
What is a refusal direction? → Read the paper ↗
Downloads · lifetime
559
313 last 30d - active
HF trending score
1
mild recent interest
Likes
4
Descendants
1
in 1 direct fork
Model age
6w ago
created 2026-08-26
Downloads over time
Now705→from0↑0%
02595177760 on Aug 26705 on Oct 11AugSepOct
Aug 26 → Oct 11 · 47 snapshots · spans 46 days

Genealogy 1 direct fork

Full fork graph →

This model's place in the market. Above: what it was derived from. Below: the tree of everything derived from it.

windowsxp811203/Qwen3.8-Flash-Next-Abliterated-NVFP4↓ 313 1 fork
gorbatjovy/qwen3.8-flash-next-abliterated-NVFP4-plefp8↓ 485

Variants by this author 3 formats · 62K downloads combined

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

Metadata

Tags
transformers safetensors qwen4_exp image-text-to-text nvfp4 fp4 modelopt vllm abliterated uncensored qwen3.8 flash-next

Related

Other by windowsxp811203
Qwen3.8-Flash-Next-Abliterated-GGUF 61K Qwen3.8-27B-Abliterated-GGUF 10K Qwen3.8-27B-Abliterated-MLX-bf16-mtp 1K Qwen3.8-Flash-Next-Abliterated 927 Qwen3.8-27B-Abliterated 545
Total size
0 B
Files
2
Quantizations
1
Registered
2026-08-26 04:02
Last updated on HF
2026-08-29 05:12
Source huggingface.co/windowsxp811203/Qwen3.8-Flash-Next-Abliterated-NVFP4 ↗

Files by quantization

Auxiliary files 2 files 2.87 KB
.gitattributes 1.48 KB a6344aac download
README.md 1.39 KB 8065c376 download

README current version from Hugging Face

tags:

  • qwen3.8-flash-next
  • qwen4-preview
  • placeholder

Qwen3.8-Flash-Next-Abliterated-NVFP4

Placeholder — build in preparation. Qwen3.8-Flash-Next (125B-A6B MoE, Qwen4 architecture
preview) is scheduled for open release on 2026-08-26 23:00 UTC+8. This repo will receive
the NVFP4 quantization of the abliterated build (Blackwell + vLLM) once three gates clear, in order:

  1. License review — the upstream license must permit derivative weights.
  2. Architecture verification — this is a new architecture, not Qwen3_5-dense; the MTP head
    layout, linear-attention naming, and the 51B n-gram embedding path all need mapping before any
    correct quantization or orthogonalization is possible. Method notes:
    nvfp4-mtp-survey.
  3. Toolchain support — llm-compressor / vLLM / llama.cpp support for the new architecture.

No ETA promised. If a correct build turns out to be impossible or the license forbids it, this
page will say so rather than shipping something broken. Track record for what "verified" means
here: Qwen3.8-27B-Abliterated ·
Qwen3.8-27B-Abliterated-NVFP4 ·
Cold-Fusion NVFP4.

README history 5 versions

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

  1. 2026-08-29Add community FP8-PLE variant (gorbatjovy) + KL stats to Decision #2ed55bee10.9 KB
    Loading...
  2. 2026-08-27card: correctness fixes from adversarial verificatione20c5a810 KB
    Loading...
  3. 2026-08-27Upload README.md with huggingface_hub5d88c729.6 KB
    Loading...
  4. 2026-08-27Upload README.md with huggingface_hubf28fee97.5 KB
    Loading...
  5. 2026-08-26Placeholder: build in preparation pending license/architecture/toolchain gates8a8a18c1.4 KB
    Loading...

Discussions 2 threads

  1. 2026-08-27PLE-FP8 Versionopen4 💬#2
    Loading...
  2. 2026-08-26Excitingopen5 💬#1
    Loading...

Continue on Hugging Face →

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.

Get the app Browse the catalog
Open in Abliteration