Base model:finetune:goekdeniz-... Base model:goekdeniz-guelmez/j... Chat Conversational Qwen3 Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/Goekdeniz-Guelmez/Josiefied-Qwen3-4B-abliterated-v2
Josiefied Qwen3 4B Abliterated V2 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)
Josiefied Qwen3 4B Abliterated V2 Parameters and Internals
| LLM Name | Josiefied Qwen3 4B Abliterated V2 |
| Repository 🤗 | https://huggingface.co/Goekdeniz-Guelmez/Josiefied-Qwen3-4B-abliterated-v2 |
| Base Model(s) | |
| Model Size | 4b |
| Required VRAM | 8.1 GB |
| Updated | 2025-07-02 |
| Maintainer | Goekdeniz-Guelmez |
| Model Type | qwen3 |
| Model Files | |
| Model Architecture | Qwen3ForCausalLM |
| Context Length | 40960 |
| Model Max Length | 40960 |
| Transformers Version | 4.51.3 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 151936 |
| Torch Data Type | bfloat16 |
| Errors | replace |
Best Alternatives to Josiefied Qwen3 4B Abliterated V2
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Jan Nano 128K | 128K / 8.1 GB | 2681 | 175 |
| Polaris 4B Preview | 128K / 8.1 GB | 1785 | 105 |
| Jan Nano 128K | 128K / 8.1 GB | 134 | 2 |
| Jan Nano | 40K / 8.1 GB | 34247 | 432 |
| Qwen3 Embedding 4B | 40K / 8.1 GB | 77957 | 85 |
| Qwen3 Reranker 4B | 40K / 8.1 GB | 35207 | 71 |
| QVikhr 3 4B Instruction | 40K / 8.1 GB | 148 | 9 |
| Qwen3 4B FP8 | 40K / 5.2 GB | 14667 | 23 |
| Qwen3 4B | 40K / 8.1 GB | 17319 | 8 |
| Jan Nano | 40K / 8.1 GB | 543 | 5 |
Note: green Score (e.g. "73.2") means that the model is better than Goekdeniz-Guelmez/Josiefied-Qwen3-4B-abliterated-v2 .
Rank the Josiefied Qwen3 4B Abliterated V2 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? 49328 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124