LLM EXPLORER 59,598 MODELS INDEXED

Holo3 35B A3B 8bit by mlx-community

By mlx-community · 22 downloads
HF Repo ↗ Copy URL

Holo3 35B A3B 8bit is an open-source language model by mlx-community. Features: 35b LLM, VRAM: 40.9GB, License: apache-2.0, Quantized, LLM Explorer Score: 0.23.

  8-bit   8bit   Action   Agent Base model:hcompany/holo3-35b-... Base model:quantized:hcompany/...   Computer use   Conversational   En   Gui agents   Image-text-to-text   Mlx   Moe   Multimodal   Pytorch   Quantized   Qwen3 5 moe   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/mlx-community/Holo3-35B-A3B-8bit 

Holo3 35B A3B 8bit Parameters and Internals

LLM NameHolo3 35B A3B 8bit
Repository 🤗https://huggingface.co/mlx-community/Holo3-35B-A3B-8bit 
Base Model(s)  Holo3 35B A3B   Hcompany/Holo3-35B-A3B
Model Size35b
Required VRAM40.9 GB
Updated2026-08-08
Maintainermlx-community
Model Typeqwen3_5_moe
Model Files  5.2 GB: 1-of-8   5.3 GB: 2-of-8   5.4 GB: 3-of-8   5.4 GB: 4-of-8   5.4 GB: 5-of-8   5.4 GB: 6-of-8   5.4 GB: 7-of-8   3.4 GB: 8-of-8
Supported Languagesen
Quantization Type8bit
Model ArchitectureQwen3_5MoeForConditionalGeneration
Licenseapache-2.0
Model Max Length262144
Transformers Version5.2.0
Tokenizer ClassTokenizersBackend
Padding Token<|endoftext|>
Errorsreplace

Best Alternatives to Holo3 35B A3B 8bit

Best Alternatives
Context / RAM
Downloads
Likes
Qwen3.6 35B A3B MLX 4bit0K / 20.5 GB5131936
Qwen3.6 35B A3B MLX 6bit0K / 28.9 GB4785922
Qwen3.6 35B A3B MLX 8bit0K / 37.8 GB4735371
Qwen3.6 35B A3B UD MLX 4bit0K / 21.6 GB15720112
Qwen3.6 35B A3B MLX 8bit0K / 37.8 GB386241
Nail Qwen3.6 35B A3B MLX 5bit0K / 27.5 GB831
Qwen3.6 35B A3B 6bit0K / 28.9 GB27428
Qwen3.6 35B A3B UD MLX 3bit0K / 17.3 GB229213
Qwen3.6 35B A3B 5bit0K / 24.7 GB16285
Ornith 1.5 35B A3B MLX 4bit0K / 19.5 GB582922
Note: green Score (e.g. "73.2") means that the model is better than mlx-community/Holo3-35B-A3B-8bit.