What are the hardware requirements for Ornith 1.5 122B MLX 4bit?

Ornith 1.5 122B MLX 4bit requires approximately 69.8 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Ornith 1.5 122B MLX 4bit and how large is it?

Ornith 1.5 122B MLX 4bit is developed by Duckets, a model with 122b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate Ornith 1.5 122B MLX 4bit?

Ornith 1.5 122B MLX 4bit is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Ornith 1.5 122B MLX 4bit by Duckets — VRAM 69.8GB

Name: Ornith 1.5 122B MLX 4bit
Author: Duckets

Ornith 1.5 122B MLX 4bit is an open-source language model by Duckets. Features: 122b LLM, VRAM: 69.8GB, License: mit, Quantized, LLM Explorer Score: 0.31.

4-bit 4bit Apple-silicon Base model:ornith-ai/ornith-1.... Base model:quantized:ornith-ai... Conversational En Image-text-to-text Lm-studio Mlx Mlx-lm Mlx-vlm Moe Ornith Quantized Qwen3 5 moe Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/Duckets/Ornith-1.5-122B-MLX-4bit

Ornith 1.5 122B MLX 4bit Parameters and Internals

LLM Name	Ornith 1.5 122B MLX 4bit
Repository 🤗	https://huggingface.co/Duckets/Ornith-1.5-122B-MLX-4bit
Base Model(s)	ornith-ai/Ornith-1.5-122B ornith-ai/Ornith-1.5-122B
Model Size	122b
Required VRAM	69.8 GB
Updated	2026-10-27
Maintainer	Duckets
Model Type	qwen3_5_moe
Model Files	5.1 GB: 1-of-14 5.2 GB: 2-of-14 5.2 GB: 3-of-14 5.2 GB: 4-of-14 5.2 GB: 5-of-14 5.2 GB: 6-of-14 5.2 GB: 7-of-14 5.2 GB: 8-of-14 5.2 GB: 9-of-14 5.2 GB: 10-of-14 5.2 GB: 11-of-14 5.2 GB: 12-of-14 5.2 GB: 13-of-14 2.3 GB: 14-of-14
Supported Languages	en
Quantization Type	4bit
Model Architecture	Qwen3_5MoeForConditionalGeneration
License	mit
Model Max Length	262144
Transformers Version	5.8.1
Tokenizer Class	Qwen3_5Tokenizer
Padding Token	<\|endoftext\|>
Errors	replace

Rank the Ornith 1.5 122B MLX 4bit capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation

Best Alternatives to Ornith 1.5 122B MLX 4bit

Best Alternatives	Context / RAM	Downloads	Likes
Qwen3.5 122B A10B 8bit	0K / 129.7 GB	4124	2
Qwen3.5 122B A10B 4bit	0K / 69.5 GB	14412	19
... 122B A10B OptiQ 2bit REAP 63B	0K / 24.7 GB	367	1
Qwen3.5 122B A10B OptiQ 2bit	0K / 46.1 GB	1093	4
Qwen3.5 122B A10B 6bit	0K / 100.1 GB	3846	3
...3.5 122B A10B GameDev MLX 4bit	0K / 44.4 GB	186	4
Qwen3.5 122B A10B 5bit	0K / 85.2 GB	654	2
Qwen3.5 122B A10B 6bit Gs32	0K / 107.9 GB	100	1
...22B A10B Vision MLX Mixed 4bit	0K / 4.7 GB	44	0
Ornith 1.5 122B	0K / 174.2 GB	60210	186

Note: green Score (e.g. "73.2") means that the model is better than Duckets/Ornith-1.5-122B-MLX-4bit.