LLM EXPLORER 58,297 MODELS INDEXED

Holo 3.1 35B A3B by Hcompany

By Hcompany · 31 downloads
HF Repo ↗ Copy URL

Holo 3.1 35B A3B is an open-source language model by Hcompany. Features: 35b LLM, VRAM: 70.6GB, LLM Explorer Score: 0.24.

  Qwen3 5 moe   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/Hcompany/Holo-3.1-35B-A3B 

Holo 3.1 35B A3B Parameters and Internals

LLM NameHolo 3.1 35B A3B
Repository 🤗https://huggingface.co/Hcompany/Holo-3.1-35B-A3B 
Model Size35b
Required VRAM70.6 GB
Updated2026-06-01
MaintainerHcompany
Model Typeqwen3_5_moe
Model Files  4.0 GB: 1-of-26   1.3 GB: 2-of-26   3.4 GB: 3-of-26   3.4 GB: 4-of-26   3.4 GB: 5-of-26   4.0 GB: 6-of-26   1.1 GB: 7-of-26   4.0 GB: 8-of-26   1.1 GB: 9-of-26   4.0 GB: 10-of-26   1.1 GB: 11-of-26   3.4 GB: 12-of-26   1.6 GB: 13-of-26   3.4 GB: 14-of-26   1.6 GB: 15-of-26   4.0 GB: 16-of-26   1.1 GB: 17-of-26   4.0 GB: 18-of-26   1.1 GB: 19-of-26   3.4 GB: 20-of-26   1.6 GB: 21-of-26   3.4 GB: 22-of-26   3.4 GB: 23-of-26   3.4 GB: 24-of-26   2.8 GB: 25-of-26   1.6 GB: 26-of-26
Model ArchitectureQwen3_5MoeForConditionalGeneration
Model Max Length262144
Transformers Version5.6.2
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Errorsreplace

Best Alternatives to Holo 3.1 35B A3B

Best Alternatives
Context / RAM
Downloads
Likes
Qwen3.6 35B A3B0K / 72.2 GB55408552648
Qwen3.5 35B A3B0K / 72.3 GB21585111482
Ornith 1.0 35B0K / 70.4 GB2869636489
KAT Coder V2.5 Dev0K / 69.7 GB17885537
Qwen3.6 35B A3B NVFP40K / 23.4 GB8788684482
Qwen AgentWorld 35B A3B0K / 69.2 GB66155665
Qwen3.6 35B A3B FP80K / 0.8 GB8984811343
XYZ Aquila Mini0K / 70.2 GB1760432
Qwen3.6 35B A3B NVFP4 Fast0K / 23.6 GB46366198
Qwen3.6 35B A3B Escha W20K / 12.3 GB3622236
Note: green Score (e.g. "73.2") means that the model is better than Hcompany/Holo-3.1-35B-A3B.