Open-source Coding with Cline and Arcee Trinity Large @juliensimonfr

Uploaded February 2026 | Updated September 2026, 2 weeks ago

I built a code review app powered by @ArceeAI 's new Trinity Large model and deployed it to a @HuggingFace Space. In this video, I use the Cline AI coding assistant with Trinity Large to explore and enhance the code review app. Open-source coding all the way! Try the app yourself and let me know what it catches in your code.

⭐️⭐️⭐️ More content on Substack at julsimon.substack.com ⭐️⭐️⭐️

Trinity Large is a 400B parameter Mixture-of-Experts model trained in 33 days for $20M — a fraction of what frontier labs spend. It has 256 experts but activates only 4 per token, so only 13B active parameters do the work. That translates to 2-3x faster inference than anything in its weight class, which you can feel in the demo when reviews come back in seconds.

Code review app: huggingface.co/spaces/juliensimon/trinity-code-reviewer
Hugging Face model page: huggingface.co/arcee-ai/Trinity-Large-Preview
OpenRouter model page: openrouter.ai/arcee-ai/trinity-large-preview
Arcee AI blog post: arcee.ai/blog/trinity-large

$Open-source Coding with Cline and Arcee Trinity Large I built a code review app powered by @ArceeAI s new Trinity Large model and deployed it to a @HuggingFace Space. In this video, I use the Cline AI coding assistant with Trinity Large to explore and enhance the code review app. Open-source coding all the way! Try the app yourself and let me know what it catches in your code. ⭐️⭐️⭐️ More content on Substack at https://julsimon.substack.com ⭐️⭐️⭐️ Trinity Large is a 400B parameter Mixture-of-Experts model trained in 33 days for $20M — a fraction of what frontier labs spend. It has 256 experts but activates only 4 per token, so only 13B active parameters do the work. That translates to 2-3x faster inference than anything in its weight class, which you can feel in the demo when reviews come back in seconds. Code review app: https://huggingface.co/spaces/juliensimon/trinity-code-reviewer Hugging Face model page: https://huggingface.co/arcee-ai/Trinity-Large-Preview OpenRouter model page: https://openrouter.ai/arcee-ai/trinity-large-preview Arcee AI blog post: https://www.arcee.ai/blog/trinity-large$

Building an AI Meeting Companion with AFM-4.5B and llama.cpp.

SLM in Action: Arcee Spark, Llama-3.1 8B, improved!

Build web apps in minutes with Replit Design Mode!

SLM in Action: Arcee Nova 72B local inference on math and code with Open WebUI and ollama

Deploying Arcee AI models in minutes with Amazon SageMaker JumpStart

LLMs from the trenches - First and foremost, it is a business discussion

Deep Dive: Compiling deep learning models, from XLA to PyTorch 2

Advanced RAG Techniques with Arcee Trinity Mini (100% Local)

Web app + Mobile + Stripe + Pitch Deck: one Replit project!

Deploy Hugging Face models on Google Cloud: directly from Vertex AI