---
title: Cloudflare/clef-omni
url: https://recentmodel.com/models/Cloudflare/clef-omni/
status: main board
published: 2026-10-09T04:10:22Z
updated: 2026-10-09T04:10:22Z
source: https://huggingface.co/Cloudflare/clef-omni
---

# Cloudflare/clef-omni

Clef-Omni is a 30B-A3B mixture-of-experts multimodal model that turns a state and a schema of typed questions into decisions. 35B params. License: apache-2.0.


- **Org:** Cloudflare
- **Released:** 2026-10-09
- **Status:** main board
- **License:** apache-2.0 (permissive)
- **Parameters:** 35.3B
- **Architecture:** Qwen3OmniMoeForConditionalGeneration
- **Task:** image-text-to-text · vision
- **Signal:** 141 HF likes · 6540 downloads

## Runs on

real quant files; sizing calculation, not tested.

- Q4 ~23.8 GB: 32GB GPU (5090), Mac 36GB, Mac 48GB, CPU only, 32GB RAM (slow)
- Q8 ~39.0 GB: 48GB GPU (RTX 6000 Ada / A6000), Mac 64GB (M1 Max), Mac 96GB, CPU only, 64GB RAM (slow)
- FP16 ~74.7 GB: 96GB GPU (RTX Pro 6000 Blackwell), 1× DGX Spark (128GB), 2× DGX Spark (256GB), Strix Halo 128GB unified (~96GB usable), Mac 128GB, Mac 192GB, Mac 256GB, Mac 512GB, CPU only, 128GB RAM (slow), CPU only, 256GB RAM (slow)

## Links

- [Hugging Face](https://huggingface.co/Cloudflare/clef-omni)
- [Ollama](https://ollama.com/library/clef)
- [MLX: mlx-community/clef-omni-4bit](https://huggingface.co/mlx-community/clef-omni-4bit)
- [MLX: mlx-community/clef-omni-8bit](https://huggingface.co/mlx-community/clef-omni-8bit)