LLM EXPLORER 65,040 MODELS INDEXED

QwenPaw Flash 4B by agentscope-ai

By agentscope-ai · 289 downloads
HF Repo ↗ Copy URL

QwenPaw Flash 4B is an open-source language model by agentscope-ai. Features: 4b LLM, VRAM: 10.4GB, License: apache-2.0, LLM Explorer Score: 0.24.

Base model:finetune:qwen/qwen3...   Base model:qwen/qwen3.5-4b   En   Qwen3 5   Region:us   Safetensors   Zh
Model Card on HF 🤗: https://huggingface.co/agentscope-ai/QwenPaw-Flash-4B 

QwenPaw Flash 4B Parameters and Internals

LLM NameQwenPaw Flash 4B
Repository 🤗https://huggingface.co/agentscope-ai/QwenPaw-Flash-4B 
Base Model(s)  Qwen/Qwen3.5-4B   Qwen/Qwen3.5-4B
Model Size4b
Required VRAM10.4 GB
Updated2026-08-05
Maintaineragentscope-ai
Model Typeqwen3_5
Model Files  10.4 GB
Supported Languagesen zh
Model ArchitectureQwen3_5ForConditionalGeneration
Licenseapache-2.0
Model Max Length262144
Transformers Version5.3.0
Tokenizer ClassTokenizersBackend
Padding Token<|endoftext|>
Errorsreplace

Best Alternatives to QwenPaw Flash 4B

Best Alternatives
Context / RAM
Downloads
Likes
AgentHorse 4B256K / 8.4 GB9737
Qwen3.5 4B0K / 9.3 GB6575502801
LightOnOCR 3 4B0K / 9.1 GB239571
NuExtract30K / 0.2 GB441570324
Agents A1 4B0K / 9.1 GB17757872
UserRepGen 4B0K / 9.1 GB100813
FrogNano 4B 26090K / 9.3 GB733113
Intern Decision 4B0K / 0.1 GB33848
Mizan V3 3B0K / 0.1 GB13518
Qwen3.5 4B Base0K / 9.3 GB22781479
Note: green Score (e.g. "73.2") means that the model is better than agentscope-ai/QwenPaw-Flash-4B.