Cloudflare/clef
main boardmodel
Clef is a 27B multimodal model that turns a state and a schema of typed questions into decisions. Dense, 27B params. Context: 256K tokens (config). License: apache-2.0.
- Org
- Cloudflare
- Released
- 2026-09-30
- Status
- main board
- License
- apache-2.0 (permissive)
- Parameters
- 27.4B
- Architecture
- dense · Qwen3_5ForConditionalGeneration
- Context
- 262,144 tokens
- Task
- image-text-to-text · vision
- Signal
- 2268 HF likes · 24335 downloads
Runs on
real quant files; need = weights + FP16 KV cache for 8K tokens + 1GB. A sizing calculation, not tested.
- Q4 ~20.8 GB: 24GB GPU (3090 / 4090), 32GB GPU (5090), 24GB GPU (7900 XTX), Mac 36GB, CPU only, 32GB RAM (slow)
- Q8 ~31.9 GB: 48GB GPU (RTX 6000 Ada / A6000), Mac 48GB, Mac 64GB (M1 Max), CPU only, 64GB RAM (slow)
- FP16 ~57.2 GB: 96GB GPU (RTX Pro 6000 Blackwell), 1× DGX Spark (128GB), 2× DGX Spark (256GB), Strix Halo 128GB unified (~96GB usable), Mac 96GB, Mac 128GB, Mac 192GB, Mac 256GB, Mac 512GB, CPU only, 128GB RAM (slow), CPU only, 256GB RAM (slow)
Links
- Hugging Face
- Ollama
- GGUF: bartowski/Cloudflare_clef-GGUF
- GGUF: ggml-org/Clef-GGUF
- MLX: mlx-community/clef-4bit
- MLX: mlx-community/clef-8bit
- MLX: mlx-community/clef-OptiQ-4bit
First published here 2026-09-30 · updated 2026-09-30 · markdown · JSON