LLM EXPLORER 60,519 MODELS INDEXED

Zera 35B A3B 4bit by Zexiry

By Zexiry · 57 downloads
HF Repo ↗ Copy URL

Zera 35B A3B 4bit is an open-source language model by Zexiry. Features: 35b LLM, VRAM: 19.5GB, License: apache-2.0, Quantized, LLM Explorer Score: 0.3.

  4-bit   4bit Base model:mlx-community/qwen3... Base model:quantized:mlx-commu...   Conversational   En   Finetuned   Mlx   Qlora   Quantized   Qwen3 5 moe   Region:us   Safetensors   Sharded   Tensorflow   Zera
Model Card on HF 🤗: https://huggingface.co/Zexiry/Zera-35B-A3B-4bit 

Zera 35B A3B 4bit Parameters and Internals

LLM NameZera 35B A3B 4bit
Repository 🤗https://huggingface.co/Zexiry/Zera-35B-A3B-4bit 
Base Model(s)  mlx-community/Qwen3.6-35B-A3B-4bit   mlx-community/Qwen3.6-35B-A3B-4bit
Model Size35b
Required VRAM19.5 GB
Updated2026-09-05
MaintainerZexiry
Model Typeqwen3_5_moe
Model Files  5.3 GB: 1-of-4   5.4 GB: 2-of-4   5.4 GB: 3-of-4   3.4 GB: 4-of-4
Supported Languagesen
Quantization Type4bit
Model ArchitectureQwen3_5MoeForConditionalGeneration
Licenseapache-2.0
Model Max Length262144
Transformers Version4.57.1
Tokenizer ClassTokenizersBackend
Padding Token<|endoftext|>
Errorsreplace

Best Alternatives to Zera 35B A3B 4bit

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
Qwen3.6 35B A3B 6bit0K / 28.9 GB27428
Qwen3.6 35B A3B UD MLX 3bit0K / 17.3 GB229213
Nail Qwen3.6 35B A3B MLX 5bit0K / 27.5 GB831
Qwen3.6 35B A3B 5bit0K / 24.7 GB16285
Ornith 1.5 35B A3B MLX 6bit0K / 28 GB342096
Note: green Score (e.g. "73.2") means that the model is better than Zexiry/Zera-35B-A3B-4bit.