LLM EXPLORER 61,652 MODELS INDEXED

Qwen3 8B UnBias Plus SFT Instruct Legacy by vector-institute

By vector-institute · 383 downloads
HF Repo ↗ Copy URL

Qwen3 8B UnBias Plus SFT Instruct Legacy is an open-source language model by vector-institute. Features: 8b LLM, VRAM: 16.4GB, Context: 40K, License: apache-2.0, Instruction-Based, LLM Explorer Score: 0.24.

  Arxiv:2606.23412 Base model:finetune:qwen/qwen3...   Base model:qwen/qwen3-8b   Bias-detection   Conversational Dataset:vector-institute/unbia...   En   Finetuned   Instruct   News-debiasing   Qwen3   Region:us   Safetensors   Sft   Sharded   Tensorflow   Unsloth
Model Card on HF 🤗: https://huggingface.co/vector-institute/Qwen3-8B-UnBias-Plus-SFT-Instruct-Legacy 

Qwen3 8B UnBias Plus SFT Instruct Legacy Parameters and Internals

LLM NameQwen3 8B UnBias Plus SFT Instruct Legacy
Repository 🤗https://huggingface.co/vector-institute/Qwen3-8B-UnBias-Plus-SFT-Instruct-Legacy 
Base Model(s)  Qwen3 8B   Qwen/Qwen3-8B
Model Size8b
Required VRAM16.4 GB
Updated2026-07-18
Maintainervector-institute
Model Typeqwen3
Instruction-BasedYes
Model Files  4.9 GB: 1-of-4   4.9 GB: 2-of-4   5.0 GB: 3-of-4   1.6 GB: 4-of-4
Supported Languagesen
Model ArchitectureQwen3ForCausalLM
Licenseapache-2.0
Context Length40960
Model Max Length40960
Tokenizer ClassQwen2Tokenizer
Padding Token<|PAD_TOKEN|>
Vocabulary Size151936
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to Qwen3 8B UnBias Plus SFT Instruct Legacy

Best Alternatives
Context / RAM
Downloads
Likes
DeepAnalyze 8B128K / 16.4 GB51293
...epSeek R1 0528 Qwen3 8B Esper3128K / 32.7 GB153
WebWorld 8B40K / 16.4 GB95064
WebWorld 32B40K / 65.8 GB34275
WebWorld 14B40K / 29.5 GB50428
...n3 8B UnBias Plus SFT Instruct40K / 16.4 GB541
QVikhr 3 8B Instruction40K / 16.4 GB384610
ThaiLLM 8B Instruct40K / 16.4 GB1760
ATLAS 8B Instruct40K / 16.4 GB232
Qwen3 8B ShiningValiant340K / 32.7 GB113
Note: green Score (e.g. "73.2") means that the model is better than vector-institute/Qwen3-8B-UnBias-Plus-SFT-Instruct-Legacy.