LLM EXPLORER 57,252 MODELS INDEXED

Qwen3.5 4B by Qwen

By Qwen · 6575502 downloads
HF Repo ↗ Copy URL

Qwen3.5 4B is an open-source language model by Qwen. Features: 4b LLM, VRAM: 9.3GB, License: apache-2.0, LLM Explorer Score: 0.44.

Base model:finetune:qwen/qwen3... Base model:qwen/qwen3.5-4b-bas...   Conversational   Deploy:azure   Deploy:sagemaker   Endpoints compatible   Eval-results   Image-text-to-text   Qwen3 5   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/Qwen/Qwen3.5-4B 

Qwen3.5 4B Parameters and Internals

LLM NameQwen3.5 4B
Repository 🤗https://huggingface.co/Qwen/Qwen3.5-4B 
Base Model(s)  Qwen/Qwen3.5-4B-Base   Qwen/Qwen3.5-4B-Base
Model Size4b
Required VRAM9.3 GB
Updated2026-08-09
MaintainerQwen
Model Typeqwen3_5
Model Files  5.3 GB: 1-of-2   4.0 GB: 2-of-2
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 4B

Model
Likes
Downloads
VRAM
Qwen3.5 4B Super Coder60377670 GB
Qwen3.5 4B AWQ 4bit187389174 GB
Qwen3.5 4B AWQ82610406 GB
Qwen3.5 4B MLX 4bit32280233 GB
Qwen3.5 4B OptiQ 4bit2378230 GB
Qwen3.5 4B Qat Lean 4bit Mlx01552 GB
Qwen3.5 4B Code Forged11728 GB
Qwen3.5 4B Mlx 4bit3162 GB
Mind Mem 4B1222 GB

Best Alternatives to Qwen3.5 4B

Best Alternatives
Context / RAM
Downloads
Likes
Agents A1 4B0K / 9.1 GB17757872
NuExtract30K / 0.2 GB441570324
Fara1.5 4B0K / 9.1 GB493439
Qwen3.5 4B Base0K / 9.3 GB22781479
DeepSeek V4 Pro Qwen3.5 4B0K / 9.3 GB34769
JOSIE 2 4B Preview0K / 9.3 GB73320
Mephisto 4B 07250K / 8.6 GB30015
Qwen3.5 4B0K / 9.3 GB13996126
JOSIE 2 4B OSS0K / 9.3 GB3257
Mephisto 4B V20K / 8.6 GB3012