Experimental3 is an open-source language model by Ba2han. Features: 2b LLM, VRAM: 4.8GB, Context: 8K, LLM Explorer Score: 0.3.
Base model:finetune:vngrs-ai/k... Base model:vngrs-ai/kumru-2b-b... Conversational Endpoints compatible Generated from trainer Mistral Region:us Safetensors Sft Trl Unsloth
Model Card on HF 🤗: https://huggingface.co/Ba2han/experimental3
Experimental3 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)
Experimental3 Parameters and Internals
| LLM Name | Experimental3 |
| Repository 🤗 | https://huggingface.co/Ba2han/experimental3 |
| Model Name | vngrs-ai/Kumru-2B-Base |
| Base Model(s) | |
| Model Size | 2b |
| Required VRAM | 4.8 GB |
| Updated | 2026-06-29 |
| Maintainer | Ba2han |
| Model Type | mistral |
| Model Files | |
| Model Architecture | MistralForCausalLM |
| Context Length | 8192 |
| Model Max Length | 8192 |
| Transformers Version | 5.8.0 |
| Tokenizer Class | TokenizersBackend |
| Padding Token | <PAD> |
| Vocabulary Size | 50176 |
Best Alternatives to Experimental3
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Trained Model Sm 1 Merged | 32K / 4 GB | 0 | 0 |
| Kara Kumru V1.0 2B | 8K / 4.8 GB | 173 | 23 |
| Kumru 2B | 8K / 4.8 GB | 1843 | 118 |
| Mistral2B GPTQ | 32K / 4 GB | 5 | 0 |
Rank the Experimental3 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? 54653 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a