LLM EXPLORER 66,845 MODELS INDEXED

Qwen3.5 2B Base by Qwen

By Qwen · 809591 downloads
HF Repo ↗ Copy URL

Qwen3.5 2B Base is an open-source language model by Qwen. Features: 2b LLM, VRAM: 4.5GB, License: apache-2.0, LLM Explorer Score: 0.35.

  Conversational   Endpoints compatible   Image-text-to-text   Qwen3 5   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/Qwen/Qwen3.5-2B-Base 

Qwen3.5 2B Base Parameters and Internals

LLM NameQwen3.5 2B Base
Repository 🤗https://huggingface.co/Qwen/Qwen3.5-2B-Base 
Model Size2b
Required VRAM4.5 GB
Updated2026-08-09
MaintainerQwen
Model Typeqwen3_5
Model Files  4.5 GB: 1-of-1
Model ArchitectureQwen3_5ForConditionalGeneration
Licenseapache-2.0
Model Max Length262144
Transformers Version4.57.0.dev0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Errorsreplace

Quantized Models of the Qwen3.5 2B Base

Model
Likes
Downloads
VRAM
Qwen3.5 2B Base 6bit14171 GB
Decisionnode Edge21702 GB
...en35 2B Base Cotypist Mlx 4bit11001 GB
Qwen3.5 2B 6bit786802 GB
Qwen3.5 2B 4bit553741 GB
Qwen3.5 2B 8bit12022 GB

Best Alternatives to Qwen3.5 2B Base

Best Alternatives
Context / RAM
Downloads
Likes
MiniCPM OCR Jev0K / 4.4 GB177080
Qwen3.5 2B0K / 4.5 GB2633311352
RynnBrain1.1 2B0K / 4.4 GB26857912
Index Translate 2B0K / 4.5 GB208965
WeMM Embedding 2B0K / 5.4 GB543368
Qwen3.8 2B Distill Heretic V20K / 4.4 GB8362
GLiDE 2B0K / 3.8 GB1094
Qwen3.5 2B0K / 4.5 GB10348718
...e Qwen3.5 2B Decision MLX Bf160K / 3.8 GB28012
Qwen3.8 2B Distill0K / 4.5 GB205624
Note: green Score (e.g. "73.2") means that the model is better than Qwen/Qwen3.5-2B-Base.