LLM EXPLORER 62,696 MODELS INDEXED

Holo4 35B A3B NVFP4 by Hcompany

By Hcompany · 196 downloads
HF Repo ↗ Copy URL

Holo4 35B A3B NVFP4 is an open-source language model by Hcompany. Features: 35b LLM, VRAM: 22.5GB, License: apache-2.0, LLM Explorer Score: 0.33.

  8-bit   Agent Base model:hcompany/holo4-35b-... Base model:quantized:hcompany/...   Compressed-tensors   Computer-use   Conversational   Endpoints compatible   Image-text-to-text   Multimodal   Qwen3 5 moe   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/Hcompany/Holo4-35B-A3B-NVFP4 

Holo4 35B A3B NVFP4 Parameters and Internals

LLM NameHolo4 35B A3B NVFP4
Repository 🤗https://huggingface.co/Hcompany/Holo4-35B-A3B-NVFP4 
Base Model(s)  Holo4 35B A3B   Hcompany/Holo4-35B-A3B
Model Size35b
Required VRAM22.5 GB
Updated2026-10-01
MaintainerHcompany
Model Typeqwen3_5_moe
Model Files  20.0 GB: 1-of-2   2.5 GB: 2-of-2
Model ArchitectureQwen3_5MoeForConditionalGeneration
Licenseapache-2.0
Model Max Length262144
Transformers Version5.10.1
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Errorsreplace

Best Alternatives to Holo4 35B A3B NVFP4

Best Alternatives
Context / RAM
Downloads
Likes
....5 35B A3B Sceptic V3 1M W4A161024K / 26.1 GB2230
...AgentWorld 35B A3B Abliterated256K / 69.2 GB96218
Ornith 1.5 35B A3B NPU2256K /  GB1131
Qwen3.6 35B A3B NPU2256K /  GB960
Qwen3.6 35B A3B0K / 72.2 GB55408552648
Qwen3.5 35B A3B0K / 72.3 GB21585111482
Qwen3.6 35B A3B NVFP40K / 23.4 GB8788684482
Ornith 1.0 35B0K / 70.4 GB1506004506
Qwen3.6 35B A3B FP80K / 0.8 GB8984811343
Qwen AgentWorld 35B A3B0K / 69.2 GB66155665
Note: green Score (e.g. "73.2") means that the model is better than Hcompany/Holo4-35B-A3B-NVFP4.