← back to catalog · registered 2026-09-09 05:55

mondk/spark-x2.5-4b-abliterated-safetensors

mondk 4.1B
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/mondk%2Fspark-x2.5-4b-abliterated-safetensors"
Response includes
  • classification m1
  • files 12
  • hub_downloads_all_time 181
  • author_summary 9 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
181
56 last 30d - stable
Likes
2
Descendants
1
in 1 direct fork
Model age
6w ago
created 2026-09-09
Downloads over time
Now227→from0↑0%
0831662500 on Sep 9227 on Oct 24227 on Oct 22SepOct
Sep 9 → Oct 24 · 46 snapshots · spans 45 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
safetensors spark2_5 llm sparkx2_5 abliterated uncensored custom_code base_model:XHToken/Spark-X2.5-4B base_model:finetune:XHToken/Spark-X2.5-4B license:apache-2.0 region:us

Related

Total size
7.66 GB
Files
12
Quantizations
1
Registered
2026-09-09 05:55
Last updated on HF
2026-09-10 10:01

Files by quantization

Auxiliary files 12 files 7.67 GB
model-00001-of-00002.safetensors 4.63 GB 62766b94 download
model-00002-of-00002.safetensors 3.03 GB 2f89f867 download
tokenizer.json 9.65 MB 2591c719 download
model.safetensors.index.json 23.6 KB b22afe3d download
tokenizer_config.json 20.3 KB 64bea0dc download
modeling_spark.py 19.0 KB 4e48c7a9 download
chat_template.jinja 4.54 KB 6c6617ee download
configuration_spark.py 4.23 KB cca611a0 download
config.json 1.99 KB 2c6a1864 download
.gitattributes 1.48 KB a6344aac download
special_tokens_map.json 613 B 98515315 download
generation_config.json 231 B 815d3009 download

README

The author did not publish a README.

README history 2 versions

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

  1. 2026-09-10Update README.mdf74b5dc345 B
    Loading...
  2. 2026-09-09Create README.mdffa8ff732 B
    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