LLM EXPLORER 62,007 MODELS INDEXED

Qwen35 Cpt Round3 by Puujeeeeeeeeeeee

By Puujeeeeeeeeeeee · 18 downloads
HF Repo ↗ Copy URL

Qwen35 Cpt Round3 is an open-source language model by Puujeeeeeeeeeeee. Features: 9.4b LLM, VRAM: 18.8GB, License: apache-2.0, LLM Explorer Score: 0.25.

Base model:finetune:puujeeeeee... Base model:puujeeeeeeeeeeee/qw...   En   Endpoints compatible   Image-text-to-text   Qwen3 5   Region:us   Safetensors   Sharded   Tensorflow   Unsloth
Model Card on HF 🤗: https://huggingface.co/Puujeeeeeeeeeeee/qwen35-cpt-round3 

Qwen35 Cpt Round3 Parameters and Internals

LLM NameQwen35 Cpt Round3
Repository 🤗https://huggingface.co/Puujeeeeeeeeeeee/qwen35-cpt-round3 
Model NamePuujeeeeeeeeeeee/qwen35-cpt-round2
Base Model(s)  Qwen35 Cpt Round2   Puujeeeeeeeeeeee/qwen35-cpt-round2
Model Size9.4b
Required VRAM18.8 GB
Updated2026-08-09
MaintainerPuujeeeeeeeeeeee
Model Typeqwen3_5
Model Files  4.9 GB: 1-of-4   5.0 GB: 2-of-4   5.0 GB: 3-of-4   3.9 GB: 4-of-4
Supported Languagesen
Model ArchitectureQwen3_5ForConditionalGeneration
Licenseapache-2.0
Model Max Length262144
Tokenizer ClassTokenizersBackend
Padding Token<|vision_pad|>
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to Qwen35 Cpt Round3

Best Alternatives
Context / RAM
Downloads
Likes
Qwen Image 2.1 PE I2I0K / 3.6 GB550142
Qwen Image 2.1 PE T2I0K / 3.6 GB188543
Qwen Image 2.1 PE I2I FP80K / 13.5 GB1122
Qwen Image 2.1 PE T2I FP80K / 13.5 GB1361
Qwen3.5FundusReasoner Base0K / 18.8 GB91
Qwen35 Cpt Round50K / 18.8 GB180
Qwen35 Cpt Round40K / 18.8 GB170
Qwen35 Cpt Round20K / 18.8 GB90
Hydra Turbo0K / 18.8 GB192
27e 20K / 18.8 GB80
Note: green Score (e.g. "73.2") means that the model is better than Puujeeeeeeeeeeee/qwen35-cpt-round3.