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

mlx-community/Josiefied-Qwen2.5-1.5B-Instruct-abliterated-v1-8bit

mlx-community Qwen 1.5B
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/mlx-community%2FJosiefied-Qwen2.5-1.5B-Instruct-abliterated-v1-8bit"
Response includes
  • classification m1
  • files 11
  • benchmarks 5 entries
  • hub_downloads_all_time 483
  • author_summary 207 models
  • readme_text full
Try next
GET/models?author=mlx-community
All 207 models by mlx-community
 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
483
67 last 30d - stable
Likes
0
Model age
2.1y ago
created 2024-09-21
Downloads over time
Now521→from0↑0%
01913825730 on Sep 18, 2024521 on Oct 11Sep '24Jan '25May '25Sep '25JanMaySep
Sep 18, 2024 → Oct 11 · 147 snapshots · spans 753 days

Benchmarks

Portrait before abliteration
Benchmarks of the base model as it stood before the refusal-removal operation. Compare with the numbers above to see what the operation cost.
Benchmark Score Source
BBH average 0.38150214035542873 OpenLLM-v2
IFEval instruct 0.30935251798561153 OpenLLM-v2
IFEval-Prompt 0.2255083179297597 OpenLLM-v2
MATH lvl 5 0.07628398791540786 OpenLLM-v2
MMLU-Pro 0.28548869680851063 OpenLLM-v2

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.

Qwen/Qwen2.5-1.5B this lineage
mlx-community/Josiefied-Qwen2.5-1.5B-Instruct-abliterated-v1-8bit↓ 67

Metadata

License
apache-2.0
Languages
en
Tags
mlx safetensors qwen2 chat text-generation conversational en base_model:Qwen/Qwen2.5-1.5B base_model:finetune:Qwen/Qwen2.5-1.5B license:apache-2.0 region:us

Related

Other by mlx-community
Qwen3.8-27B-Uncensored-OptiQ-4bit 16K Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-8bit 7K Qwen3.8-Flash-Next-Uncensored-oQ5e-mtp 5K Josiefied-Qwen3-4B-abliterated-v1-4bit 4K Huihui-Qwen3.6-35B-A3B-Claude-4.7-Opus-abliterated-mlx-8bit 4K
Same base model
Goekdeniz-Guelmez/Josiefied-Qwen2.5-1.5B-Instruct-abliterated-v1 905 nooruiit-864/qwen2.5-1.5b-base-ai-safety-domain-lora 155 mlx-community/Josiefied-Qwen2.5-1.5B-Instruct-abliterated-v1-4bit 114 mlx-community/Josiefied-Qwen2.5-1.5B-Instruct-abliterated-v1-2bit 85 mlx-community/Josiefied-Qwen2.5-1.5B-Instruct-abliterated-v1-f16 68
Total size
1.53 GB
Files
11
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2024-09-24 13:21
Source huggingface.co/mlx-community/Josiefied-Qwen2.5-1.5B-Instruct-abliterated-v1-8bit ↗ Base model Qwen/Qwen2.5-1.5B ↗

Files by quantization

Auxiliary files 11 files 1.54 GB
model.safetensors 1.53 GB 7392f95f download
tokenizer.json 6.71 MB d24314ef download
vocab.json 2.65 MB 4783fe10 download
merges.txt 1.59 MB 31349551 download
model.safetensors.index.json 50.4 KB ca694471 download
tokenizer_config.json 7.13 KB 8adf747c download
.gitattributes 1.48 KB a6344aac download
README.md 924 B eaccbf1a download
config.json 783 B 1dee14cc download
special_tokens_map.json 613 B ac23c0aa download
added_tokens.json 605 B 482ced46 download

README current version from Hugging Face

base_model: Qwen/Qwen2.5-1.5B
language:

mlx-community/Josiefied-Qwen2.5-1.5B-Instruct-abliterated-v1-8bit

The Model mlx-community/Josiefied-Qwen2.5-1.5B-Instruct-abliterated-v1-8bit was converted to MLX format from Goekdeniz-Guelmez/Josiefied-Qwen2.5-1.5B-Instruct-abliterated-v1 using mlx-lm version 0.13.1.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("mlx-community/Josiefied-Qwen2.5-1.5B-Instruct-abliterated-v1-8bit")
response = generate(model, tokenizer, prompt="hello", verbose=True)

README history 2 versions

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

  1. 2024-09-24Update README.mdacbef5b924 B
    Loading...
  2. 2024-09-21Upload folder using huggingface_hub (#1)1d42fe8914 B
    Loading...

Discussions 2 threads

  1. 2025-04-27PRImprove language tagopen1 💬#2
    Loading...
  2. 2024-09-21PRUpload folder using huggingface_hubmerged3 💬#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