← back to catalog · registered 2026-11-20 10:04

zviratko/Qwen3.8-Flash-Next-Uncensored-oQ3.5h-mtp-plefp8

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-oQ3.5h-mtp-plefp8"
Response includes
  • classification m-uncensored
  • files 58
  • 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
54
Likes
0
Model age
2d ago
created 2026-11-20
Downloads over time
Now 54 → from 0 ↑ 0%
0204059 0 on Nov 20 54 on Nov 22 Nov
Nov 20 → Nov 22 · 3 snapshots · spans 2 days

Metadata

Tags
mlx safetensors qwen4_exp oq quantized mtp 3-bit region:us

Related

Total size
109 GB
Files
58
Quantizations
1
Registered
2026-11-20 10:04
Last updated on HF
2026-11-20 09:55

Files by quantization

Auxiliary files 58 files 109 GB
model-00013-of-00019.safetensors 5.68 GB b936743f download
model-00014-of-00019.safetensors 5.68 GB 84e6cf2a download
model-00009-of-00019.safetensors 5.49 GB bbc718ca download
model-00010-of-00019.safetensors 5.10 GB 199a1d6a download
model-00011-of-00019.safetensors 4.90 GB 3223f386 download
model-00012-of-00019.safetensors 4.70 GB ba3ba667 download
model-00016-of-00019.safetensors 4.70 GB 340ad887 download
model-00015-of-00019.safetensors 4.70 GB ef4b6a60 download
model-00018-of-00019.safetensors 4.70 GB 6a0ce922 download
model-00017-of-00019.safetensors 4.70 GB a17c21bf download
model-00008-of-00019.safetensors 4.06 GB 40ef38d1 download
model-00019-of-00019.safetensors 3.53 GB 98bad96e download
model-00007-of-00019.safetensors 1.86 GB 21825419 download
ple-table-00021-of-00026.safetensors 1.86 GB 589eb8e3 download
ple-table-00022-of-00026.safetensors 1.86 GB e156781f download
ple-table-00023-of-00026.safetensors 1.86 GB eb181c1f download
ple-table-00024-of-00026.safetensors 1.86 GB f2d43dc9 download
ple-table-00025-of-00026.safetensors 1.86 GB 90aa0731 download
ple-table-00001-of-00026.safetensors 1.86 GB 78fbf62e download
ple-table-00002-of-00026.safetensors 1.86 GB 61d2ae90 download
ple-table-00003-of-00026.safetensors 1.86 GB 300624bc download
ple-table-00004-of-00026.safetensors 1.86 GB 3343bf23 download
ple-table-00005-of-00026.safetensors 1.86 GB eaebd034 download
ple-table-00006-of-00026.safetensors 1.86 GB 2154a700 download
ple-table-00007-of-00026.safetensors 1.86 GB ff263182 download
ple-table-00008-of-00026.safetensors 1.86 GB daef8264 download
ple-table-00009-of-00026.safetensors 1.86 GB 466fff85 download
ple-table-00010-of-00026.safetensors 1.86 GB 1e9f9525 download
ple-table-00011-of-00026.safetensors 1.86 GB f4cea84d download
ple-table-00012-of-00026.safetensors 1.86 GB 1596c995 download
ple-table-00013-of-00026.safetensors 1.86 GB 7ed2b52a download
ple-table-00014-of-00026.safetensors 1.86 GB 30be95c3 download
ple-table-00015-of-00026.safetensors 1.86 GB 2f02a0fb download
ple-table-00016-of-00026.safetensors 1.86 GB 32f1d869 download
ple-table-00017-of-00026.safetensors 1.86 GB 2b373954 download
ple-table-00018-of-00026.safetensors 1.86 GB 4a165072 download
ple-table-00019-of-00026.safetensors 1.86 GB ef475031 download
ple-table-00020-of-00026.safetensors 1.86 GB 3e0a0236 download
ple-table-00026-of-00026.safetensors 1.12 GB bce95cae download
model-00001-of-00019.safetensors 1.02 GB 4e0b3435 download
model-00002-of-00019.safetensors 40.0 B 60d95b10 download
model-00003-of-00019.safetensors 40.0 B 60d95b10 download
model-00004-of-00019.safetensors 40.0 B 60d95b10 download
model-00005-of-00019.safetensors 40.0 B 60d95b10 download
model-00006-of-00019.safetensors 40.0 B 60d95b10 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 366 KB 5454f1bc download
config.json 227 KB c5a2e4e8 download
oq_imatrix_report.json 58.4 KB 408226ce download
ple_transplant_report.json 34.8 KB 10ccd9fd 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 1.34 KB f9314cd7 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

Qwen3.8-Flash-Next-Uncensored-oQ3.5h-mtp-plefp8

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

The effective average is 23.208 bits/weight excluding the N-gram embedding table, or 12.645 bits/weight for the complete checkpoint.

Quantization and Bit Distribution

Storage format Logical weights Share of total Tensor storage Effective bits/weight
Affine 4-bit, group 64 2.601B 3.528% 1.363 GiB 4.50
Affine 6-bit, group 64 0.883B 1.198% 0.668 GiB 6.50
Affine 8-bit, group 128 0.241B 0.327% 0.231 GiB 8.25
Affine 8-bit, group 64 3.763B 5.105% 3.723 GiB 8.50
FP8 (E4M3) 51.200B 69.456% 47.684 GiB 8.00
BF16 0.610B 0.828% 1.137 GiB 16.00
U32 14.418B 19.559% 53.711 GiB 32.00
I64 0.000B 0.000% 0.000 GiB 64.00
Total 73.717B 100% 108.518 GiB 12.645

Storage Breakdown

Component Logical weights Storage
Language model 19.460B 62.951 GB / 58.628 GiB
N-gram embedding 51.200B 51.200 GB / 47.684 GiB
Vision 0.449B 0.898 GB / 0.836 GiB
MTP head 2.607B 1.471 GB / 1.370 GiB
Total 73.717B 116.520 GB / 108.518 GiB

README history 1 version

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

  1. 2026-11-20 Upload Qwen3.8-Flash-Next-Uncensored-oQ3.5h-mtp-plefp8 via oMLX 5200eb6 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