BQTrans New is an open-source language model by SKNahin. Features: 532.2m LLM, VRAM: 1.1GB, Context: 128K, LLM Explorer Score: 0.19.
Autotrain compatible Base model:finetune:sknahin/ba... Base model:sknahin/banglaqwen-... Conversational Endpoints compatible Full Generated from trainer Llama-factory Qwen2 Region:us Safetensors
Model Card on HF 🤗: https://huggingface.co/SKNahin/BQTrans-new
BQTrans New 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)
BQTrans New Parameters and Internals
| LLM Name | BQTrans New |
| Repository 🤗 | https://huggingface.co/SKNahin/BQTrans-new |
| Base Model(s) | |
| Model Size | 532.2m |
| Required VRAM | 1.1 GB |
| Updated | 2025-09-19 |
| Maintainer | SKNahin |
| Model Type | qwen2 |
| Model Files | |
| Model Architecture | Qwen2ForCausalLM |
| Context Length | 131072 |
| Model Max Length | 131072 |
| Transformers Version | 4.51.2 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 194498 |
| Torch Data Type | bfloat16 |
| Errors | replace |
Rank the BQTrans New 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? 52265 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