TeleOCR MXFP8 is an open-source language model by sahilchachra. Features: 1.3b LLM, VRAM: 1.9GB, Context: 125K, License: apache-2.0, LLM Explorer Score: 0.31.
| LLM Name | TeleOCR MXFP8 |
| Repository 🤗 | https://huggingface.co/sahilchachra/TeleOCR-MXFP8 |
| Base Model(s) | |
| Model Size | 1.3b |
| Required VRAM | 1.9 GB |
| Updated | 2026-10-05 |
| Maintainer | sahilchachra |
| Model Type | qwen2_5_vl |
| Model Files | |
| Supported Languages | zh en |
| Model Architecture | Qwen2_5_VLForConditionalGeneration |
| License | apache-2.0 |
| Context Length | 128000 |
| Model Max Length | 128000 |
| Transformers Version | 4.57.1 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 151936 |
| Errors | replace |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| TeleOCR INT8 | 125K / 2 GB | 129 | 1 |