# Ornith 1.5 Brings a Lean 35B MoE to Open Weights

> The MIT-licensed model activates just 3B parameters per token, borrowing the Qwen3.5 MoE design for text and reasoning tasks.

Published by The Open Weights on Aug 18, 2026. Canonical: https://theopenweights.com/news/ornith-1-5-35b-a3b-w6je

## Key facts

- Company: Ornith Ai
- Model: Ornith-1.5-122B
- Version: 1.5
- Category: Text / LLM
- Modalities: Text / LLM, Reasoning
- License: MIT (Open weights, commercial use allowed)
- Parameters: 35B (mixture of experts)
- Active parameters: 3B
- Context window: 262K tokens
- Architecture: Qwen3_5MoeForConditionalGeneration
- Precision: BF16
- Weights size: 71.9 GB
- Significance: minor
- Published: 2026-08-18
- Last verified: 2026-09-05
- Hugging Face: https://huggingface.co/ornith-ai/Ornith-1.5-35B-A3B
- Canonical URL: https://theopenweights.com/news/ornith-1-5-35b-a3b-w6je

Ornith AI has published **Ornith-1.5-35B-A3B**, a mixture-of-experts language model that leans on sparsity to keep inference costs down. While the model holds 35 billion parameters in total, only about 3 billion are active for any given token, according to its [Hugging Face repository](https://huggingface.co/ornith-ai/Ornith-1.5-35B-A3B).

The release is built on the Qwen3.5 MoE architecture and targets both general text generation and reasoning. It ships under an MIT license, one of the more permissive options for commercial and research use, which lowers the barrier for developers who want to fine-tune or deploy it without restrictive terms.

## Why it matters

The appeal of a 35B/3B-active setup is efficiency: MoE models can offer the knowledge capacity of a larger network while running at the speed and memory footprint closer to a much smaller dense model. That tradeoff has become a popular recipe for teams building on top of Qwen's architecture.

- Total parameters: 35B, with roughly 3B active per token
- Architecture: Qwen3.5 MoE
- License: MIT
- Focus: text generation and reasoning

As a smaller, incremental release, Ornith 1.5 is less about headline benchmarks and more about giving the open-weights community another permissively licensed MoE to experiment with. Details such as context length and evaluation results were not specified in the release record, so prospective users will want to check the repository directly before building against it.

## Get the model

- [Hugging Face](https://huggingface.co/ornith-ai/Ornith-1.5-35B-A3B)

## Sources

- [ornith-ai/Ornith-1.5-35B-A3B](https://huggingface.co/ornith-ai/Ornith-1.5-35B-A3B) — Hugging Face, Aug 18, 2026

---
Source: The Open Weights (https://theopenweights.com/). Aggregated and written by Claude, curated by humans. Cite as: "Ornith 1.5 Brings a Lean 35B MoE to Open Weights", The Open Weights, Aug 18, 2026, https://theopenweights.com/news/ornith-1-5-35b-a3b-w6je