What are the hardware requirements for Ornith 1.5 122B FP8?

Ornith 1.5 122B FP8 requires approximately 90.1 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Ornith 1.5 122B FP8 and how large is it?

Ornith 1.5 122B FP8 is developed by ornith-ai, 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 FP8?

Ornith 1.5 122B FP8 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 FP8 by ornith-ai — VRAM 90.1GB

Name: Ornith 1.5 122B FP8
Author: ornith-ai

Ornith 1.5 122B FP8 is an open-source language model by ornith-ai. Features: 122b LLM, VRAM: 90.1GB, License: mit.

Compressed-tensors Conversational Endpoints compatible Image-text-to-text Qwen3 5 moe Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/ornith-ai/Ornith-1.5-122B-FP8

Ornith 1.5 122B FP8 Parameters and Internals

LLM Name	Ornith 1.5 122B FP8
Repository 🤗	https://huggingface.co/ornith-ai/Ornith-1.5-122B-FP8
Model Size	122b
Required VRAM	90.1 GB
Updated	2026-10-24
Maintainer	ornith-ai
Model Type	qwen3_5_moe
Model Files	2.6 GB: 1-of-62 2.5 GB: 2-of-62 2.6 GB: 3-of-62 2.5 GB: 4-of-62 1.7 GB: 5-of-62 1.0 GB: 6-of-62 2.5 GB: 7-of-62 2.6 GB: 8-of-62 2.5 GB: 9-of-62 1.7 GB: 10-of-62 1.0 GB: 11-of-62 2.5 GB: 12-of-62 2.6 GB: 13-of-62 2.5 GB: 14-of-62 1.7 GB: 15-of-62 1.0 GB: 16-of-62 2.5 GB: 17-of-62 2.6 GB: 18-of-62 2.5 GB: 19-of-62 1.7 GB: 20-of-62 1.0 GB: 21-of-62 2.5 GB: 22-of-62 2.6 GB: 23-of-62 2.5 GB: 24-of-62 1.7 GB: 25-of-62 1.0 GB: 26-of-62 2.5 GB: 27-of-62 2.6 GB: 28-of-62 2.5 GB: 29-of-62 1.7 GB: 30-of-62 1.0 GB: 31-of-62 2.5 GB: 32-of-62 2.6 GB: 33-of-62 2.5 GB: 34-of-62 1.7 GB: 35-of-62 1.0 GB: 36-of-62 2.5 GB: 37-of-62 2.6 GB: 38-of-62 2.5 GB: 39-of-62 1.7 GB: 40-of-62 1.0 GB: 41-of-62 2.5 GB: 42-of-62 2.6 GB: 43-of-62
Model Architecture	Qwen3_5MoeForConditionalGeneration
License	mit
Transformers Version	5.8.1

Rank the Ornith 1.5 122B FP8 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 FP8

Best Alternatives	Context / RAM	Downloads	Likes
Qwen3.5 122B A10B NVFP4	0K / 83.5 GB	248732	49
Qwen3.5 122B A10B	0K / 248.6 GB	2139628	605
Qwen3.5 122B A10B	0K / 248.6 GB	1680	8
Qwen3.5 122B A10B	0K / 248.6 GB	45	1
Qwen3.5 122B A10B Abliterated	0K / 248.6 GB	108	5
Qwen3.5 122B A10B FP8	0K / 126.3 GB	1271983	112
Qwen3.5 122B A10B NVFP4	0K / 74 GB	18267	18
...en3.5 122B A10B Int4 AutoRound	0K / 72 GB	142311	45
AREX Base	0K / 164.2 GB	394	22
...2.6 Destill Healed Abliterated	0K / 245.1 GB	1143	15

Note: green Score (e.g. "73.2") means that the model is better than ornith-ai/Ornith-1.5-122B-FP8.