LLM EXPLORER 65,695 MODELS INDEXED

XYZ Aquila Mini OptiQ 4bit by mlx-community

By mlx-community · 34 downloads
HF Repo ↗ Copy URL

XYZ Aquila Mini OptiQ 4bit is an open-source language model by mlx-community. Features: 34.7b LLM, VRAM: 36.3GB, License: apache-2.0, Quantized, LLM Explorer Score: 0.24.

  4-bit   4bit   Agentic-search Base model:quantized:xyzailab/... Base model:xyzailab/xyz-aquila...   Conversational   Mixed-precision   Mlx   Optiq   Quantized   Qwen3.6   Qwen3 5 moe   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/mlx-community/XYZ-Aquila-mini-OptiQ-4bit 

XYZ Aquila Mini OptiQ 4bit Parameters and Internals

LLM NameXYZ Aquila Mini OptiQ 4bit
Repository 🤗https://huggingface.co/mlx-community/XYZ-Aquila-mini-OptiQ-4bit 
Base Model(s)  XYZ Aquila Mini   XYZAILab/XYZ-Aquila-mini
Model Size34.7b
Required VRAM36.3 GB
Updated2026-07-27
Maintainermlx-community
Model Typeqwen3_5_moe
Model Files  5.2 GB: 1-of-7   5.3 GB: 2-of-7   5.3 GB: 3-of-7   5.3 GB: 4-of-7   5.3 GB: 5-of-7   5.3 GB: 6-of-7   4.6 GB: 7-of-7
Quantization Type4bit
Model ArchitectureQwen3_5MoeForConditionalGeneration
Licenseapache-2.0
Model Max Length262144
Transformers Version5.12.1
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Errorsreplace

Quantized Models of the XYZ Aquila Mini OptiQ 4bit

Model
Likes
Downloads
VRAM
...quila Mini OptiQ 4bit REAP 18B218119 GB

Best Alternatives to XYZ Aquila Mini OptiQ 4bit

Best Alternatives
Context / RAM
Downloads
Likes
Sage A1.5 OptiQ 4bit0K / 22.1 GB4064
Nex N2.5 Mini MLX 4bit0K / 19.5 GB10776
Occamy 1.0 MLX 4bit0K / 19.5 GB7392
Nex N2.5 Mini OptiQ 4bit0K / 22.2 GB2822
Agents A1 OptiQ 4bit0K / 22.2 GB8913
...CybersecurityLLM V1.0 Mlx 4Bit0K / 19.5 GB76547
KAT Coder V2.5 Dev OptiQ 4bit0K / 21.9 GB1143
Edge0 35B A3B Preview0K / 19.6 GB95198
MLExpert0K / 69.7 GB59215
Affine 5dfqbbh8ev Sft0K / 69.3 GB3880
Note: green Score (e.g. "73.2") means that the model is better than mlx-community/XYZ-Aquila-mini-OptiQ-4bit.