Kumru 2B is an open-source language model by vngrs-ai. Features: 2b LLM, VRAM: 4.8GB, Context: 8K, License: apache-2.0, LLM Explorer Score: 0.24.
| LLM Name | Kumru 2B |
| Repository 🤗 | https://huggingface.co/vngrs-ai/Kumru-2B |
| Model Size | 2b |
| Required VRAM | 4.8 GB |
| Updated | 2026-08-04 |
| Maintainer | vngrs-ai |
| Model Type | mistral |
| Model Files | |
| Supported Languages | tr |
| Model Architecture | MistralForCausalLM |
| License | apache-2.0 |
| Context Length | 8192 |
| Model Max Length | 8192 |
| Transformers Version | 4.49.0 |
| Tokenizer Class | PreTrainedTokenizer |
| Padding Token | <PAD> |
| Vocabulary Size | 50176 |
| Torch Data Type | bfloat16 |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Trained Model Sm 1 Merged | 32K / 4 GB | 0 | 0 |
| Experimental3 | 8K / 4.8 GB | 335 | 0 |
| Kara Kumru V1.0 2B | 8K / 4.8 GB | 52 | 23 |
| Mistral2B GPTQ | 32K / 4 GB | 6 | 0 |