Clef — local AI model by Cloudflare
Written by Jakub Rusinowski · Last updated
Cloudflare's decision models, Clef 27B and Clef-Flash 9B: typed questions in, a probability per option out, in one scoring pass with no text generation. Both are in Ollama's library and accept images.
Variants
The smallest Clef variant needs about 6 GB of VRAM at Q4_K_M — quantized weights plus framework overhead, before any KV cache.
| Model | VRAM at Q4 | VRAM | Context | Run it |
|---|---|---|---|---|
| Clef 27B → 27B | ~17.3 GB | 64K (documented) | ollama pull clef | |
| Clef-Flash 9B → 9B | ~6.5 GB | 64K (documented) | ollama pull clef-flash |
Memory is quantized weights plus overhead at Q4_K_M, from the same engine as the GPU & VRAM checker.
How to run Clef locally
Install Ollama, then pull the tag.
ollama pull clefPick a size above for its own VRAM figure, speed estimate and install command.
Licence
Commercial use permitted. No usage restrictions beyond attribution.
Applies to: Clef 27B, Clef-Flash 9BRecommended GPU
The cheapest catalogued GPU that runs Clef locally (min 6 GB VRAM) is the Intel Arc B570 (10 GB).
Clef — frequently asked questions
How much VRAM does Clef need?
Clef needs about 6 GB VRAM at Q4_K_M quantization for its smallest variant. Variants: Clef 27B (17 GB, Q4_K_M); Clef-Flash 9B (6 GB, Q4_K_M). On Apple Silicon, unified memory counts toward this requirement.
Can I run Clef on an RTX 4090 (24 GB)?
Yes — Clef runs on an RTX 4090 (24 GB) and other 24 GB cards such as the RTX 3090. Smaller variants also fit comfortably on 8–16 GB GPUs at Q4_K_M.
What quantization should I use for Clef?
Q4_K_M is the best balance of quality and VRAM for Clef in most cases. Choose Q8_0 for near-lossless quality if you have spare VRAM, or smaller quants (Q3/Q2) only when memory is tight.
How do I run Clef locally?
Clef is a decision model: it is called over an HTTP endpoint (/v1/systemone), not chatted with. Where a variant is available in Ollama 0.35 or newer, pull it with `ollama pull` and send requests to the local server; the others ship their own server. Each variant page shows the exact commands for that model.