Mini Pozor is an open-source language model by erhj3eh3ehweg. Features: 2.6b LLM, VRAM: 5.2GB, Context: 8K, LLM Explorer Score: 0.17.
| LLM Name | Mini Pozor |
| Repository 🤗 | https://huggingface.co/erhj3eh3ehweg/mini-pozor |
| Model Size | 2.6b |
| Required VRAM | 5.2 GB |
| Updated | 2026-08-03 |
| Maintainer | erhj3eh3ehweg |
| Model Type | gemma2 |
| Model Files | |
| Model Architecture | Gemma2ForCausalLM |
| Context Length | 8192 |
| Model Max Length | 8192 |
| Transformers Version | 4.46.0 |
| Tokenizer Class | GemmaTokenizer |
| Padding Token | <unk> |
| Vocabulary Size | 256000 |
| Torch Data Type | bfloat16 |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Test | 8K / 5.2 GB | 33 | 0 |
| SFT Peft | 8K / 5.2 GB | 12 | 0 |
| SFT Fft | 8K / 5.2 GB | 8 | 0 |
| Gemma 2 Full Dare Peft | 8K / 10.5 GB | 10 | 0 |
| FFT Model Gemma | 8K / 5.2 GB | 7 | 0 |
| Vera V1.1 Instruct | 8K / 5.2 GB | 12 | 0 |
| SAFETY FULL FT VECTOR | 8K / 10.5 GB | 11 | 0 |
| SAFETY PEFT VECTOR | 8K / 10.5 GB | 7 | 0 |
| RESTA Sft Dare Full Ft | 8K / 10.5 GB | 5 | 0 |
| Gemma2 DARE Sft Peft | 8K / 10.5 GB | 13 | 0 |