LLM EXPLORER 59,420 MODELS INDEXED

3B Htmlonly by winstcha

By winstcha · 7 downloads
HF Repo ↗ Copy URL

3B Htmlonly is an open-source language model by winstcha. Features: 3b LLM, VRAM: 6.2GB, Context: 32K, License: other, Instruction-Based, LLM Explorer Score: 0.16.

  Autotrain Base model:finetune:qwen/qwen2... Base model:qwen/qwen2.5-3b-ins...   Conversational   Endpoints compatible   Instruct   Peft   Qwen2   Region:us   Safetensors   Sharded   Tensorboard   Tensorflow
Model Card on HF 🤗: https://huggingface.co/winstcha/3B-htmlonly 

3B Htmlonly Parameters and Internals

LLM Name3B Htmlonly
Repository 🤗https://huggingface.co/winstcha/3B-htmlonly 
Base Model(s)  Qwen/Qwen2.5-3B-Instruct   Qwen/Qwen2.5-3B-Instruct
Model Size3b
Required VRAM6.2 GB
Updated2026-08-01
Maintainerwinstcha
Model Typeqwen2
Instruction-BasedYes
Model Files  5.0 GB: 1-of-2   1.2 GB: 2-of-2   0.0 GB
Model ArchitectureQwen2ForCausalLM
Licenseother
Context Length32768
Model Max Length32768
Transformers Version4.48.0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size151665
Torch Data Typefloat16
Errorsreplace

Best Alternatives to 3B Htmlonly

Best Alternatives
Context / RAM
Downloads
Likes
VibeThinker 3B128K / 6.2 GB52745806
VibeThinker 3B128K / 6.2 GB3610
Saba2 3B128K / 6.2 GB60
Tessa T1 3B117K / 6.2 GB105
UIGEN T1.5 3B117K / 6.2 GB71
Qwen2.5 3B Instruct32K / 6.2 GB5889234545
...er 3B Instruct Spider Sft Grpo32K / 6.2 GB5061
...2.5 3B Instruct SFT In WebShop32K / 6.8 GB3471
SmallThinker 3B Preview32K / 6.8 GB30529412
Qwen2.5 3B Haizi32K / 6.2 GB740
Note: green Score (e.g. "73.2") means that the model is better than winstcha/3B-htmlonly.