What are the hardware requirements for Ornith 1.5 35B A3B 2bit MLX?

Ornith 1.5 35B A3B 2bit MLX requires approximately 11.7 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Ornith 1.5 35B A3B 2bit MLX and how large is it?

Ornith 1.5 35B A3B 2bit MLX is developed by lukaskremla, a model with 35b 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 35B A3B 2bit MLX?

Ornith 1.5 35B A3B 2bit MLX is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Ornith 1.5 35B A3B 2bit MLX by lukaskremla — VRAM 11.7GB

Name: Ornith 1.5 35B A3B 2bit MLX
Author: lukaskremla

Ornith 1.5 35B A3B 2bit MLX is an open-source language model by lukaskremla. Features: 35b LLM, VRAM: 11.7GB, License: mit, Quantized, LLM Explorer Score: 0.3.

2-bit 2bit Affine Base model:ornith-ai/ornith-1.... Base model:quantized:ornith-ai... Bf16-vision-tower Conversational Group-size-64 Image-text-to-text Long-context Mlx Mlx-vlm Multilingual Multimodal Ornith Ornith-1.5 Ornith-1.5-35b-a3b Quantized Qwen Qwen3 5 Qwen3 5 moe Reasoning Region:us Rtn Safetensors Sharded Tensorflow Tool-use Video Vision Vision-language Weight-only-quantization

Model Card on HF 🤗: https://huggingface.co/lukaskremla/Ornith-1.5-35B-A3B-2bit-MLX

Ornith 1.5 35B A3B 2bit MLX Parameters and Internals

LLM Name	Ornith 1.5 35B A3B 2bit MLX
Repository 🤗	https://huggingface.co/lukaskremla/Ornith-1.5-35B-A3B-2bit-MLX
Model Name	Ornith-1.5-35B-A3B 2-bit MLX
Base Model(s)	ornith-ai/Ornith-1.5-35B-A3B ornith-ai/Ornith-1.5-35B-A3B
Model Size	35b
Required VRAM	11.7 GB
Updated	2026-09-04
Maintainer	lukaskremla
Model Type	qwen3_5_moe
Model Files	5.4 GB: 1-of-3 5.3 GB: 2-of-3 1.0 GB: 3-of-3
Quantization Type	2bit
Model Architecture	Qwen3_5MoeForConditionalGeneration
License	mit
Model Max Length	262144
Transformers Version	5.8.1
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|endoftext\|>
Errors	replace

Rank the Ornith 1.5 35B A3B 2bit MLX 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 35B A3B 2bit MLX

Best Alternatives	Context / RAM	Downloads	Likes
Qwen3.6 35B A3B MLX 4bit	0K / 20.5 GB	513193	6
Qwen3.6 35B A3B MLX 6bit	0K / 28.9 GB	478592	2
Qwen3.6 35B A3B MLX 8bit	0K / 37.8 GB	473537	1
Qwen3.6 35B A3B UD MLX 4bit	0K / 21.6 GB	15720	112
Qwen3.6 35B A3B MLX 8bit	0K / 37.8 GB	3862	41
Qwen3.6 35B A3B 6bit	0K / 28.9 GB	2742	8
Nail Qwen3.6 35B A3B MLX 5bit	0K / 27.5 GB	83	1
Qwen3.6 35B A3B UD MLX 3bit	0K / 17.3 GB	2292	13
Qwen3.6 35B A3B 5bit	0K / 24.7 GB	1628	5
Ornith 1.5 35B A3B MLX 6bit	0K / 28 GB	34209	6

Note: green Score (e.g. "73.2") means that the model is better than lukaskremla/Ornith-1.5-35B-A3B-2bit-MLX.