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

nqd145/Gemma-4-E2B-it-abliterated-litertlm

nqd145 Gemma 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/nqd145%2FGemma-4-E2B-it-abliterated-litertlm"
Response includes
  • classification m1
  • files 4
  • author_summary 1 models
  • readme_text full
Try next
GET/models?family=gemma&method=m1
Sibling gemma 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 · 30-day
0
Likes
21
Model age
6mo ago
created 2026-04-13
Downloads over time
Now0→from0↑0%
00110 on Apr 150 on Oct 11AprMayJunJulAugSepOct
Apr 15 → Oct 11 · 65 snapshots · spans 179 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.

huihui-ai/Huihui-gemma-4-E2B-it-abliterated↓ 2,918 this lineage
nqd145/Gemma-4-E2B-it-abliterated-litertlm

Metadata

License
apache-2.0
Languages
en
Tags
transformers gemma litert-lm tflite abliterated text-generation en base_model:google/gemma-4-E2B-it base_model:finetune:google/gemma-4-E2B-it license:apache-2.0 region:us

Related

Same base model
mradermacher/Huihui-gemma-4-E2B-it-abliterated-GGUF 3K mradermacher/Huihui-gemma-4-E2B-it-abliterated-i1-GGUF 899 EZCon/Huihui-gemma-4-E2B-it-abliterated-4bit-mlx 157 EZCon/Huihui-gemma-4-E2B-it-abliterated-4bit-g32-mxfp4-mixed_4_8-mlx 148 EZCon/Huihui-gemma-4-E2B-it-abliterated-8bit-mlx 133
Total size
0 B
Files
4
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2026-04-13 10:19
Source huggingface.co/nqd145/Gemma-4-E2B-it-abliterated-litertlm ↗ Base model huihui-ai/Huihui-gemma-4-E2B-it-abliterated →

Files by quantization

Auxiliary files 4 files 4.72 GB
Gemma-4-E2B-it-abliterated.litertlm 4.72 GB 3bb97959 download
.gitattributes 1.55 KB a587c868 download
README.md 1.39 KB 5628c1d0 download
allow_list.json 869 B f1ddf884 download

README current version from Hugging Face

license: apache-2.0
base_model:

  • huihui-ai/Huihui-gemma-4-E2B-it-abliterated
  • google/gemma-4-E2B-it
    tags:
  • gemma
  • litert-lm
  • tflite
  • abliterated
    pipeline_tag: text-generation
    language:
  • en
    library_name: transformers
    model_type: gemma
    inference: false

Gemma-4-E2B-it-abliterated (LiteRT-LM)

LiteRT-LM export of huihui-ai/Huihui-gemma-4-E2B-it-abliterated for on-device / edge inference workflows.

Model File

  • Gemma-4-E2B-it-abliterated.litertlm

Source

  • Base checkpoint: huihui-ai/Huihui-gemma-4-E2B-it-abliterated
  • Export pipeline: safetensors-to-litertlm

Export Notes

  • Export format: .litertlm (LiteRT-LM bundle)
  • Quantization: INT8 profile (dynamic_wi8_afp32)
  • Intended runtime: litert-lm CLI / LiteRT-LM compatible apps

Quick Start (CPU)

litert-lm run ./Gemma-4-E2B-it-abliterated.litertlm --prompt "Hi" --backend cpu

Limitations

  • Behavior may differ from the original HF checkpoint due to conversion/quantization/runtime differences.
  • Some export profiles that reduce memory pressure can alter section topology and runtime behavior.

Safety

This model may generate unsafe or incorrect content. Evaluate carefully for your use case and apply application-level safeguards where needed.

License

Please follow the upstream license and usage terms of:

  • huihui-ai/Huihui-gemma-4-E2B-it-abliterated
  • underlying Gemma model family terms

README history 1 version

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

  1. 2026-04-13Upload README.md with huggingface_hub966f5611.4 KB
    Loading...

Discussions 5 threads

  1. 2026-05-08vision_backend is not availableopen1 💬#5
    Loading...
  2. 2026-04-30Best way to convert safetensors to litertlmopen1 💬#4
    Loading...
  3. 2026-04-20PRUpload Gemma-4-E2B-it-abliterated.litertlmopen1 💬#3
    Loading...
  4. 2026-04-16INT4 ?open1 💬#2
    Loading...
  5. 2026-04-15Can we please get Gemma-4-E4B-it-abliterated-litertlmopen1 💬#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