SuperGemma 4 12B Abliterated Nvf4 is an open-source language model by Jiunsong. Features: 12b LLM, VRAM: 6.7GB, License: apache-2.0, LLM Explorer Score: 0.32.
4-bit Abliterated Base model:jiunsong/supergemma... Base model:quantized:jiunsong/... Conversational En Gemma4 Ko Mlx Nvfp4 Quantized Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/Jiunsong/SuperGemma-4-12b-abliterated-nvf4
SuperGemma 4 12B Abliterated Nvf4 Benchmarks
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
What is the LLM Explorer Rank (Score)
SuperGemma 4 12B Abliterated Nvf4 Parameters and Internals
| LLM Name | SuperGemma 4 12B Abliterated Nvf4 |
| Repository 🤗 | https://huggingface.co/Jiunsong/SuperGemma-4-12b-abliterated-nvf4 |
| Base Model(s) | |
| Model Size | 12b |
| Required VRAM | 6.7 GB |
| Updated | 2026-06-26 |
| Maintainer | Jiunsong |
| Model Type | gemma4 |
| Model Files | |
| Supported Languages | en ko |
| Model Architecture | Gemma4ForConditionalGeneration |
| License | apache-2.0 |
| Transformers Version | 5.12.1 |
| Tokenizer Class | GemmaTokenizer |
| Padding Token | <pad> |
| Vocabulary Size | 262144 |
Rank the SuperGemma 4 12B Abliterated Nvf4 Capabilities
🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟
What open-source LLMs or SLMs are you in search of? 54565 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a