Tiny Aya 3.3B L2 Thinker BF16 GGUF is an open-source language model by AMAImedia. Features: 3.3b LLM, VRAM: 6.7GB, Context: 4882K, License: cc-by-nc-4.0, Quantized.
| LLM Name | Tiny Aya 3.3B L2 Thinker BF16 GGUF |
| Repository 🤗 | https://huggingface.co/AMAImedia/Tiny-Aya-3.3B-L2-Thinker-BF16-GGUF |
| Base Model(s) | |
| Model Size | 3.3b |
| Required VRAM | 6.7 GB |
| Updated | 2026-09-13 |
| Maintainer | AMAImedia |
| Model Type | cohere2 |
| Model Files | |
| Supported Languages | am ar eu bn bg ca zh cs en fi fr de el ha he hi hu ig id ga it ja jv km ko lt ms mt no fa pl pa ru sk sw ta te th tr uk ur vi yo zu |
| GGUF Quantization | Yes |
| Quantization Type | gguf |
| Model Architecture | Cohere2ForCausalLM |
| License | cc-by-nc-4.0 |
| Context Length | 5000000 |
| Model Max Length | 5000000 |
| Transformers Version | 4.56.2.4 |
| Tokenizer Class | CohereTokenizerFast |
| Padding Token | <PAD> |
| Vocabulary Size | 262144 |