LLM EXPLORER 65,894 MODELS INDEXED

PhysBrain1.5 8B by DeepCybo

By DeepCybo · 638 downloads
HF Repo ↗ Copy URL

PhysBrain1.5 8B is an open-source language model by DeepCybo. Features: 8b LLM, VRAM: 17.8GB, Instruction-Based, LLM Explorer Score: 0.3.

  Arxiv:2609.14973   Any-to-any Base model:finetune:qwen/qwen3... Base model:qwen/qwen3-vl-8b-in...   Embodied-ai   En   Endpoints compatible   Image-text-to-text   Instruct   Multimodal   Qwen3 vl   Region:us   Robotics   Safetensors   Sharded   Spatial-reasoning   Tensorflow   Vision   Vision-language-model   Zh
Model Card on HF 🤗: https://huggingface.co/DeepCybo/PhysBrain1.5-8B 

PhysBrain1.5 8B Parameters and Internals

LLM NamePhysBrain1.5 8B
Repository 🤗https://huggingface.co/DeepCybo/PhysBrain1.5-8B 
Base Model(s)  Qwen3 VL 8B Instruct   Qwen/Qwen3-VL-8B-Instruct
Model Size8b
Required VRAM17.8 GB
Updated2026-09-26
MaintainerDeepCybo
Model Typeqwen3_vl
Instruction-BasedYes
Model Files  4.9 GB: 1-of-4   5.0 GB: 2-of-4   5.0 GB: 3-of-4   2.9 GB: 4-of-4
Supported Languagesen zh
Model ArchitectureQwen3VLForConditionalGeneration
Model Max Length262144
Transformers Version5.12.1
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Errorsreplace

Best Alternatives to PhysBrain1.5 8B

Best Alternatives
Context / RAM
Downloads
Likes
Qwen3 VL 8B Instruct0K / 17.5 GB44943291037
Qwen3 VL 8B Instruct FP80K / 10.6 GB310860477
AesCode 8B0K / 17.5 GB35657
Qwen3vl Resume Parser0K / 17.5 GB2574553
UHR BAT20K / 17.5 GB12215
...e Builder Qwen3 VL 8B Instruct0K / 17.5 GB693
Qwen3 VL 8B Heretic 1.3.00K / 17.5 GB465312
Qwen3 VL 8B Instruct0K / 17.5 GB411
... Qwen3vl8b Coldstart Step162000K / 17.5 GB360
Uzocr 8B0K / 17.5 GB661
Note: green Score (e.g. "73.2") means that the model is better than DeepCybo/PhysBrain1.5-8B.