What base models is Ornith-1.0 built on?

Ornith-1.0 is built on top of pretrained Gemma 4 and Qwen 3.5, both licensed under Apache 2.0.

Can I use Ornith-1.0 commercially?

Yes. Ornith-1.0 is MIT licensed, and its underlying base models (Gemma 4 and Qwen 3.5) are both Apache 2.0 licensed, making the licenses compatible for commercial use.

What hardware do I need to run it?

The 35B MoE variant has been run using the GGUF format in a 20GB quantized version, suggesting it can run on consumer-grade hardware with sufficient memory.

Large Language ModelsSimon Willison's WeblogJun 29, 2026Jun 30, 2026, 04:00 JST1 min read

DeepReinforce releases Ornith-1.0, open-source coding AI model

Send on LINE

Key takeaway

DeepReinforce released Ornith-1.0, a free, open-source AI model designed for coding tasks, in four size variants.
Built from Apache 2.0–licensed base models and available under MIT license, it achieves top-tier performance on coding benchmarks and can run on consumer hardware, making it accessible to developers and smaller teams.

3 Key Points

What happened
DeepReinforce, a new AI company, released Ornith-1.0, an open-source model (MIT licensed) available in four variants—9B Dense, 31B Dense, 35B MoE, and 397B MoE. Built on pretrained Gemma 4 and Qwen 3.5, it achieves state-of-the-art performance among open-source models of comparable size on coding benchmarks.
Why it matters
The model's Apache 2.0–compatible licenses (inherited from Gemma 4 and Qwen 3.5) make it freely usable for commercial and derivative work. Early testing shows it handles multi-step agent workflows efficiently, suggesting it may be useful for developers building systems that perform coding tasks autonomously.
What to watch
The 35B MoE variant runs via GGUF format on consumer hardware (20GB version tested); the model generated output at 103 tokens per second in generation tests. DeepReinforce's earliest known publication is a June 2025 paper on CUDA optimization.

Ask the AI about this article →

Summaries like this, in your inbox every morning.

Get news like this every morning — free

FAQ

What base models is Ornith-1.0 built on?: Ornith-1.0 is built on top of pretrained Gemma 4 and Qwen 3.5, both licensed under Apache 2.0.
Can I use Ornith-1.0 commercially?: Yes. Ornith-1.0 is MIT licensed, and its underlying base models (Gemma 4 and Qwen 3.5) are both Apache 2.0 licensed, making the licenses compatible for commercial use.
What hardware do I need to run it?: The 35B MoE variant has been run using the GGUF format in a 20GB quantized version, suggesting it can run on consumer-grade hardware with sufficient memory.

Simon Willison's WeblogRead Original Article

Send on LINE

Get the latest Large Language Models news every morning

For example, today's edition would include:

DataAgent launches with $10M to auto-fix Kubernetes faultsSiliconANGLE AI · 48m ago
SK Hynix custom HBM boosts inference up to 5.15xDIGITIMES Asia · 48m ago
Nvidia Earnings: Boring by Design, Avoiding a Consolidated WorldStratechery (Ben Thompson) · 48m ago

AI-summarized, only the topics you pick — one digest a day via Email, Slack, or Discord.

Subscribe free →

Free · takes 30 seconds · unsubscribe anytimeWhat is AIToday? →