LLM EXPLORER 66,978 MODELS INDEXED

Qwen3.5 0.8B Base by unsloth

By unsloth · 4439 downloads
HF Repo ↗ Copy URL

Qwen3.5 0.8B Base is an open-source language model by unsloth. Features: 0.8b LLM, VRAM: 1.7GB, License: apache-2.0, LLM Explorer Score: 0.26.

Base model:finetune:qwen/qwen3... Base model:qwen/qwen3.5-0.8b-b...   Endpoints compatible   Image-text-to-text   Qwen3 5   Region:us   Safetensors   Unsloth
Model Card on HF 🤗: https://huggingface.co/unsloth/Qwen3.5-0.8B-Base 

Qwen3.5 0.8B Base Parameters and Internals

LLM NameQwen3.5 0.8B Base
Repository 🤗https://huggingface.co/unsloth/Qwen3.5-0.8B-Base 
Base Model(s)  Qwen/Qwen3.5-0.8B-Base   Qwen/Qwen3.5-0.8B-Base
Model Size0.8b
Required VRAM1.7 GB
Updated2026-08-10
Maintainerunsloth
Model Typeqwen3_5
Model Files  1.7 GB
Model ArchitectureQwen3_5ForConditionalGeneration
Licenseapache-2.0
Model Max Length262144
Transformers Version5.3.0.dev0
Tokenizer ClassTokenizersBackend
Padding Token<|vision_pad|>
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to Qwen3.5 0.8B Base

Best Alternatives
Context / RAM
Downloads
Likes
... 0.8B Weight Space Programming0K / 1.8 GB129790
OvisOCR30K / 1.7 GB4972109
Qwen3.5 0.8B0K / 1.8 GB2839884655
OvisOCR20K / 1.7 GB83978506
Xiaomi OCR 00K / 1.8 GB16009164
... 0.8B Weight Space Programming0K / 1.8 GB22756
MinerU2.5 Flash 0.8B0K / 1.7 GB231
Qwen3.5 0.8B Astra WeightEdit0K / 1.8 GB14119
Qwen3.5 0.8B Base0K / 1.8 GB82805492
LightOnOCR 3 0.8B0K / 1.7 GB131848
Note: green Score (e.g. "73.2") means that the model is better than unsloth/Qwen3.5-0.8B-Base.