LLM EXPLORER 66,704 MODELS INDEXED

Piccolo 4B by agentscope-ai

By agentscope-ai · 145 downloads
HF Repo ↗ Copy URL

Piccolo 4B is an open-source language model by agentscope-ai. Features: 4b LLM, VRAM: 8.4GB, License: apache-2.0.

  Agentscope Base model:finetune:qwen/qwen3...   Base model:qwen/qwen3.5-4b   Bidirectional-attention   Decision-model   En   Endpoints compatible   Image-text-to-text   Qwen3 5   Qwenpaw   Region:us   Safetensors   Sharded   Tensorflow   Zh
Model Card on HF 🤗: https://huggingface.co/agentscope-ai/Piccolo-4B 

Piccolo 4B Parameters and Internals

LLM NamePiccolo 4B
Repository 🤗https://huggingface.co/agentscope-ai/Piccolo-4B 
Base Model(s)  Qwen/Qwen3.5-4B   Qwen/Qwen3.5-4B
Model Size4b
Required VRAM8.4 GB
Updated2026-11-05
Maintaineragentscope-ai
Model Typeqwen3_5
Model Files  5.3 GB: 1-of-2   3.1 GB: 2-of-2   0.9 GB
Supported Languagesen zh
Model ArchitectureQwen3_5ForConditionalGeneration
Licenseapache-2.0
Model Max Length262144
Transformers Version4.57.0.dev0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Errorsreplace

Best Alternatives to Piccolo 4B

Best Alternatives
Context / RAM
Downloads
Likes
AgentHorse 4B256K / 8.4 GB9737
Qwen3.5 4B0K / 9.3 GB6575502801
NuExtract30K / 0.2 GB441570324
LightOnOCR 3 4B0K / 9.1 GB239571
Agents A1 4B0K / 9.1 GB17757872
FrogNano 4B 26090K / 9.3 GB733113
Qwen3.5 4B Base0K / 9.3 GB22781479
UserRepGen 4B0K / 9.1 GB100813
Intern Decision 4B0K / 0.1 GB33848
Tev1 4B Experimental0K / 9.3 GB153916
Note: green Score (e.g. "73.2") means that the model is better than agentscope-ai/Piccolo-4B.