← back to catalog · registered 2026-08-22 13:56

johnsmith968530/Goekdeniz-Guelmez-Josiefied-Qwen3-14B-abliterated-v3-MLX-8bit

johnsmith968530 Qwen 15B 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/johnsmith968530%2FGoekdeniz-Guelmez-Josiefied-Qwen3-14B-abliterated-v3-MLX-8bit"
Response includes
  • classification m1
  • files 16
  • hub_downloads_all_time 600
  • author_summary 1 models
  • readme_text full
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)
Refusal direction extracted via
Extraction technique

Difference-of-means

Confidence
MEDIUM
Why we say so
primary_method=M1; difference-of-means is the reference extraction for M1/M3 (Arditi 2024)
Downloads · lifetime
600
40 last 30d - cooling
Likes
0
Model age
10mo ago
created 2025-11-21
Downloads over time
Now612→from27↑2,167%
022444767127 on Nov 19, 2025612 on Oct 12612 on Oct 11Nov '25JanMarMayJulSep
Nov 19, 2025 → Oct 12 · 87 snapshots · spans 327 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

Tags
mlx safetensors qwen3 chat text-generation conversational base_model:Goekdeniz-Guelmez/Josiefied-Qwen3-14B-abliterated-v3 base_model:quantized:Goekdeniz-Guelmez/Josiefied-Qwen3-14B-abliterated-v3 8-bit region:us

Related

Total size
15.5 GB
Files
16
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2025-11-21 21:35

Files by quantization

Auxiliary files 16 files 15.5 GB
model-00001-of-00004.safetensors 5.00 GB 5cb075e4 download
model-00002-of-00004.safetensors 4.98 GB efd60d56 download
model-00003-of-00004.safetensors 4.69 GB b0aa4edc download
model-00004-of-00004.safetensors 835 MB 072c994b download
tokenizer.json 10.9 MB aeb13307 download
vocab.json 2.65 MB 4783fe10 download
merges.txt 1.59 MB 31349551 download
model.safetensors.index.json 84.3 KB e9727595 download
tokenizer_config.json 5.28 KB ddaf6980 download
chat_template.jinja 4.02 KB 699ff8df download
.gitattributes 1.53 KB 52373fe2 download
README.md 1.09 KB ed9223ac download
config.json 990 B 7ca11af1 download
added_tokens.json 707 B b54f9135 download
special_tokens_map.json 613 B ac23c0aa download
generation_config.json 214 B e4f1d319 download

README current version from Hugging Face


tags:

  • chat
  • mlx
    base_model: Goekdeniz-Guelmez/Josiefied-Qwen3-14B-abliterated-v3
    pipeline_tag: text-generation
    library_name: mlx

johnsmith968530/Goekdeniz-Guelmez-Josiefied-Qwen3-14B-abliterated-v3-MLX-8bit

This model johnsmith968530/Goekdeniz-Guelmez-Josiefied-Qwen3-14B-abliterated-v3-MLX-8bit was
converted to MLX format from Goekdeniz-Guelmez/Josiefied-Qwen3-14B-abliterated-v3
using mlx-lm version 0.28.3.

export MODEL1_MAJOR="Goekdeniz-Guelmez"
export MODEL1_MINOR="Josiefied-Qwen3-14B-abliterated-v3"
export MODEL1_Q_BITS="8"
export MODEL1_DTS="$(date -z UTC +%Y%m%d_%H%M%SZ)"

echodo () { echo "$@" && "$@"; }
mkdir -p /tmp/mlx/lm/convert

echodo time mlx_lm.convert \
  --hf-path "$MODEL1_MAJOR/$MODEL1_MINOR" \
  --mlx-path "/tmp/mlx/lm/convert/$MODEL1_DTS" \
  --quantize \
  --q-bits "$MODEL1_Q_BITS" \
  --upload-repo \
    "johnsmith968530/$MODEL1_MAJOR-$MODEL1_MINOR-MLX-${MODEL1_Q_BITS}bit"

README history 2 versions

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

  1. 2025-11-21Update README.md41bc7a01.1 KB
    Loading...
  2. 2025-11-21Add files using upload-large-folder toold8ab2021.1 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