LLM EXPLORER 55,709 MODELS INDEXED

Ornith 1.0 9B OptiQ 4bit by mlx-community

By mlx-community · 1656 downloads
HF Repo ↗ Copy URL

Ornith 1.0 9B OptiQ 4bit is an open-source language model by mlx-community. Features: 9b LLM, VRAM: 7.1GB, License: mit, Quantized.

  4-bit   4bit   8bit   Apple-silicon Base model:deepreinforce-ai/or... Base model:quantized:deepreinf...   Conversational   Image-text-to-text   Mixed-precision   Mlx   Optiq   Quantized   Qwen3.5   Qwen3 5   Region:us   Safetensors   Sharded   Tensorflow   Vision   Vision-language
Model Card on HF 🤗: https://huggingface.co/mlx-community/Ornith-1.0-9B-OptiQ-4bit 

Ornith 1.0 9B OptiQ 4bit Parameters and Internals

LLM NameOrnith 1.0 9B OptiQ 4bit
Repository 🤗https://huggingface.co/mlx-community/Ornith-1.0-9B-OptiQ-4bit 
Base Model(s)  deepreinforce-ai/Ornith-1.0-9B   deepreinforce-ai/Ornith-1.0-9B
Model Size9b
Required VRAM7.1 GB
Updated2026-08-08
Maintainermlx-community
Model Typeqwen3_5
Model Files  5.3 GB: 1-of-2   1.8 GB: 2-of-2
Quantization Type4bit
Model ArchitectureQwen3_5ForConditionalGeneration
Licensemit
Model Max Length262144
Transformers Version5.8.1
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Errorsreplace

Best Alternatives to Ornith 1.0 9B OptiQ 4bit

Best Alternatives
Context / RAM
Downloads
Likes
Ornith 1.0 9B 4bit0K / 5.9 GB97919
Qwen3.5 9B MLX 4bit0K / 5.9 GB22827151
Qwen3.5 9B OptiQ 4bit0K / 7.1 GB1013686
Ornith 1.0 9B 8bit0K / 10.4 GB20792
Ornith 1.0 9B 6bit0K / 8.1 GB8282
... Opus Reasoning Distilled 4bit0K / 5 GB137025
Qwopus3.5 9B V3 4bit0K / 5.9 GB652
Qwen3.5 9B 4bit0K / 5.9 GB1756612
Qwen3.5 9B 6bit0K / 8.1 GB7905
Fara1.5 9B 8bit0K / 10.4 GB1201
Note: green Score (e.g. "73.2") means that the model is better than mlx-community/Ornith-1.0-9B-OptiQ-4bit.