Model Card on HF 🤗: https://huggingface.co/eternisai/anonymizer-0.6B-SFTonly
Anonymizer 0.6B SFTonly 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)
Anonymizer 0.6B SFTonly Parameters and Internals
| LLM Name | Anonymizer 0.6B SFTonly |
| Repository 🤗 | https://huggingface.co/eternisai/anonymizer-0.6B-SFTonly |
| Model Size | 0.6b |
| Required VRAM | 1.2 GB |
| Updated | 2025-08-29 |
| Maintainer | eternisai |
| Model Type | qwen3 |
| Model Files | |
| Supported Languages | en |
| Model Architecture | Qwen3ForCausalLM |
| License | mit |
| Context Length | 40960 |
| Model Max Length | 40960 |
| Transformers Version | 4.53.2 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 151936 |
| Torch Data Type | float16 |
| Errors | replace |
Best Alternatives to Anonymizer 0.6B SFTonly
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Qwen3 Reranker 0.6B | 40K / 1.2 GB | 292957 | 212 |
| Kimina Prover Distill 0.6B | 40K / 1.5 GB | 3669 | 1 |
| Anonymizer 0.6B | 40K / 1.2 GB | 95 | 2 |
| Qwen3 0.6B FP8 | 40K / 1.1 GB | 15293 | 48 |
| Luth 0.6B Instruct | 40K / 1.2 GB | 519 | 8 |
| Qwen3 0.6B | 40K / 1.2 GB | 23691 | 14 |
| OuteTTS 1.0 0.6B | 40K / 1.2 GB | 1319 | 89 |
| Qwen3 0.6B | 40K / 1.2 GB | 4288 | 3 |
| RStar Coder Qwen3 0.6B | 40K / 1.2 GB | 91 | 4 |
| Qwen3 0.6B MLX Bf16 | 40K / 1.2 GB | 1859 | 5 |
Note: green Score (e.g. "73.2") means that the model is better than eternisai/anonymizer-0.6B-SFTonly .
Rank the Anonymizer 0.6B SFTonly 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? 50995 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124