Cloudflare/clef-omni
main boardmodel
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; need = weights + FP16 KV cache for 8K tokens + 1GB. A 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
First published here 2026-10-09 · updated 2026-10-09 · markdown · JSON