← back to catalog · registered 2026-11-18 22:04

zviratko/Qwen3.8-Flash-Next-Uncensored-oQ4h-mtp

zviratko 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/zviratko%2FQwen3.8-Flash-Next-Uncensored-oQ4h-mtp"
Response includes
  • classification m-uncensored
  • files 32
  • author_summary 18 models
  • readme_text full
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M-U
Primary method

Uncensored (method unknown)

No other method signals detected in this model.
Confidence
LOW
Why this label 3 signals
Weak or ambiguous signals. Best guess based on catalog patterns; treat as tentative and check the evidence below.
  • 'uncensored' in name/tags but no 'abliterated' marker
  • method not identifiable from author declaration alone
  • may be DPO fine-tune, prompt engineering, or unknown technique
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
90
Likes
0
Descendants
1
in 1 direct fork
Model age
3d ago
created 2026-11-18
Downloads over time
Now 90 → from 0 ↑ 0%
0336699 0 on Nov 18 90 on Nov 22 Nov
Nov 18 → Nov 22 · 5 snapshots · spans 4 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.

Metadata

Tags
mlx safetensors qwen4_exp oq quantized mtp base_model:orcarouter/Qwen3.8-Flash-Next-Uncensored base_model:quantized:orcarouter/Qwen3.8-Flash-Next-Uncensored 4-bit region:us

Related

Total size
100 GB
Files
32
Quantizations
1
Registered
2026-11-18 22:04
Last updated on HF
2026-11-18 21:54

Files by quantization

Auxiliary files 32 files 100 GB
model-00016-of-00020.safetensors 5.37 GB f320c03a download
model-00017-of-00020.safetensors 5.37 GB 1f15daa4 download
model-00014-of-00020.safetensors 5.37 GB 5c49b154 download
model-00019-of-00020.safetensors 5.37 GB dc00bd0d download
model-00018-of-00020.safetensors 5.37 GB 61eb71bb download
model-00015-of-00020.safetensors 5.27 GB b5603ce3 download
model-00020-of-00020.safetensors 5.27 GB 852691ab download
model-00009-of-00020.safetensors 5.27 GB de46b64e download
model-00010-of-00020.safetensors 5.27 GB d3f5778d download
model-00013-of-00020.safetensors 5.18 GB 8a1efa25 download
model-00012-of-00020.safetensors 5.08 GB f732e330 download
model-00011-of-00020.safetensors 4.98 GB b71ca82e download
model-00001-of-00020.safetensors 4.75 GB f437c47c download
model-00007-of-00020.safetensors 4.67 GB 6971ec2e download
model-00006-of-00020.safetensors 4.66 GB 6932d98d download
model-00005-of-00020.safetensors 4.66 GB 6ad381a0 download
model-00003-of-00020.safetensors 4.66 GB a3f43ee6 download
model-00004-of-00020.safetensors 4.66 GB 0d0e8868 download
model-00002-of-00020.safetensors 4.66 GB 4451478c download
model-00008-of-00020.safetensors 4.29 GB 1408e018 download
tokenizer.json 12.2 MB 0997f410 download
vocab.json 6.41 MB 0aa0ce06 download
merges.txt 3.20 MB a494e019 download
model.safetensors.index.json 412 KB 1acc866d download
config.json 268 KB cb921e09 download
oq_imatrix_report.json 58.4 KB ebc9e374 download
tokenizer_config.json 17.5 KB 5de744b3 download
chat_template.jinja 8.74 KB c0c686f9 download
.gitattributes 1.53 KB 52373fe2 download
README.md 607 B fe3047e2 download
preprocessor_config.json 390 B 2ea84a43 download
generation_config.json 202 B 023756cf download

README current version from Hugging Face


library_name: mlx
tags:

  • mlx
  • oq
  • quantized
  • mtp
    base_model:
  • orcarouter/Qwen3.8-Flash-Next-Uncensored

Qwen3.8-Flash-Next-Uncensored-oQ4h-mtp

This model was quantized using oQ (oMLX v0.8.0) mixed-precision quantization.

Storage Breakdown

Component Logical weights Storage
Language model 22.852B 73.154 GB / 68.130 GiB
N-gram embedding 51.200B 32.000 GB / 29.802 GiB
Vision 0.449B 0.898 GB / 0.836 GiB
MTP head 2.607B 1.513 GB / 1.409 GiB
Total 77.109B 107.565 GB / 100.178 GiB

README history 2 versions

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

  1. 2026-11-18 Update README.md ae5755e 607 B
    Loading...
  2. 2026-11-18 Upload Qwen3.8-Flash-Next-Uncensored-oQ4h-mtp via oMLX 0f927b6 1.3 KB
    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