Llavaqwen3 1.7B Finetune is an open-source language model by KKHYA. Features: 1.7b LLM, VRAM: 4.7GB, Context: 40K, License: apache-2.0, Fine-Tuned, LLM Explorer Score: 0.31.
Base model:finetune:qwen/qwen3... Base model:qwen/qwen3-1.7b Conversational Endpoints compatible Finetuned Generated from trainer Llava qwen3 Region:us Safetensors
Model Card on HF 🤗: https://huggingface.co/KKHYA/llavaqwen3-1.7b-finetune
Llavaqwen3 1.7B Finetune 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)
Llavaqwen3 1.7B Finetune Parameters and Internals
| LLM Name | Llavaqwen3 1.7B Finetune |
| Repository 🤗 | https://huggingface.co/KKHYA/llavaqwen3-1.7b-finetune |
| Base Model(s) | |
| Model Size | 1.7b |
| Required VRAM | 4.7 GB |
| Updated | 2026-04-27 |
| Maintainer | KKHYA |
| Model Type | llava_qwen3 |
| Model Files | |
| Model Architecture | LlavaQwen3ForCausalLM |
| License | apache-2.0 |
| Context Length | 40960 |
| Model Max Length | 40960 |
| Transformers Version | 4.51.0 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|extra_0|> |
| Vocabulary Size | 151936 |
| Torch Data Type | bfloat16 |
| Errors | replace |
Rank the Llavaqwen3 1.7B Finetune 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? 53254 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