LLM EXPLORER 62,007 MODELS INDEXED

Holo2 8B by Hcompany

By Hcompany · 1924 downloads
HF Repo ↗ Copy URL

Holo2 8B is an open-source language model by Hcompany. Features: 8b LLM, VRAM: 17.5GB, License: apache-2.0, LLM Explorer Score: 0.37, ELO: 1329.

  Action   Agent Base model:finetune:qwen/qwen3... Base model:qwen/qwen3-vl-8b-th...   Computer use   Conversational   Deploy:azure   En   Endpoints compatible   Eval-results   Gui agents   Image-text-to-text   Multimodal   Pytorch   Qwen3 vl   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/Hcompany/Holo2-8B 

Holo2 8B Benchmarks

LMSys ELO 1329 vs 1272 (so35) 4.5%
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

Holo2 8B Parameters and Internals

LLM NameHolo2 8B
Repository 🤗https://huggingface.co/Hcompany/Holo2-8B 
Base Model(s)  Qwen3 VL 8B Thinking   Qwen/Qwen3-VL-8B-Thinking
Model Size8b
Required VRAM17.5 GB
Updated2026-08-08
MaintainerHcompany
Model Typeqwen3_vl
Model Files  5.0 GB: 1-of-4   4.9 GB: 2-of-4   4.9 GB: 3-of-4   2.7 GB: 4-of-4
Supported Languagesen
Model ArchitectureQwen3VLForConditionalGeneration
Licenseapache-2.0
Model Max Length262144
Transformers Version4.57.0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Errorsreplace

Best Alternatives to Holo2 8B

Best Alternatives
Context / RAM
Downloads
Likes
Qwen3 VL 8B Instruct0K / 17.5 GB44943291037
PhysBrain1.5 8B0K / 17.8 GB46927
Qwen3 VL 8B Instruct FP80K / 10.6 GB310860477
Qwen3vl Resume Parser0K / 17.5 GB2574553
Qwen3 VL 8B Thinking0K / 17.5 GB107015220
Qwen3 VL 8B Heretic 1.3.00K / 17.5 GB465312
ArmorOCR0K / 17.5 GB1959
Om Logistics Pod New V00K / 17.5 GB1900
Qwen3 VL 8B VQA SFT0K / 17.5 GB1990
UI Venus 1.5 8B0K / 17.5 GB843529
Note: green Score (e.g. "73.2") means that the model is better than Hcompany/Holo2-8B.