Text analysisImage + textComputer-use agents

Clef

Decision models: they do not write text but read a situation (text, JSON, an image, video frames) and return in one pass the probability of each answer to typed questions: yes or no, pick one, rate on a scale. The agent gets ready numbers instead of parsing free text.

Developer
Cloudflare, USA
First release
Oct 2026
Latest release
Oct 2026
Sizes
27B and 9B (Clef-flash)
License
Commercial use allowedApache 2.0
Russian
Not stated
Ready-made builds
GGUF
Running
Available in OllamaNeeds a GPU
Industries
Customer support, Documents and accounting, Security, Software development
Deploy on your server Hugging Face

What it does

  • sorting requests and tickets into categories with a probability
  • checking a document or photo against a list of questions (is everything stated, is there a violation)
  • choosing the next step of an agent without parsing a text answer
  • rating risk or urgency on a scale

Where it is used

customer support and ticket handlingdocument management and request checkssecurity and moderationAI agents and process automation

Hardware requirements

LaptopLaptop or regular PC, up to 8 GB of VRAM — smaller versions
fits
1 GPUOne GPU with 16–80 GB — mid-size versions
fits
ClusterServer with several GPUs — flagship versions
no versions

Versions

  1. Clef-flash 9B (на базе Qwen3.5-9B)
  2. Clef 27B (на базе Qwen3.8-27B)

How to run it

With Ollama — the fastest wayInstall Ollama on your computer or server and find the model in its library by name. Good enough to try the model on your own tasks in one evening.Find it in the Ollama library
On your own serverWeights are downloaded from Hugging Face and served with vLLM (load and API) or llama.cpp (modest hardware). The model then runs in a closed network with no per-request fees.Hugging Face
How much hardware you needCalculate the VRAM for the model size, context length and number of concurrent requests.Open the hardware calculator

I can set this up end to end: pick the model size, deploy it on your server and connect it to your systems. Quantization compresses a model so it takes less video memory and runs on more modest hardware. Answers change slightly, so quality is checked on your own examples.

Frequently asked questions

Can Clef be used in a commercial project?

Yes. License: Apache 2.0. It allows commercial use, but it is still worth having a lawyer review the license before launch.

What hardware does Clef need?

At minimum: Laptop or regular PC, up to 8 GB of VRAM — smaller versions. Without a GPU the model is not practical. You can calculate the exact VRAM for your model size and context in the hardware calculator.

Does Clef support Russian?

The model card does not list languages, so Russian support cannot be promised — it has to be tested on your own examples.

Where can I download Clef and what does it cost?

The Clef weights are open and free to download. You only pay for the hardware it runs on and for the setup. Source links are at the bottom of this page.

How I deploy it for clients

  1. SelectionI pick the model size for your task and hardware and test it on your examples.
  2. DeploymentI deploy it on your server or in a closed network and provide an API.
  3. Fine-tuningI fine-tune it on your data (LoRA) or connect a knowledge base — whichever is cheaper for the task.
  4. IntegrationI connect it to your CRM, ERP, bot, website or team chat and set up monitoring.

Similar models

TextQwenAlibaba · ChinaCommercial use with conditions

A family of language models with strong Russian language support, from small versions for a laptop to a flagship on par with commercial APIs.

DetailsTextGemmaGoogle · USACommercial use allowed

Compact Google models that run well on a single computer; larger versions understand images. Includes CodeGemma for code, FunctionGemma 270M for function calling and the fast DiffusionGemma.

DetailsModeration and safetyAegis / Nemotron Safety GuardNVIDIA · USACommercial use with conditions

NVIDIA content filters for bots, with separate models for keeping the conversation on topic and detecting jailbreaks. Safety Guard v3 was trained on 9 languages; Russian was tested only without fine-tuning.

Details

Source: huggingface.co/Cloudflare/clef. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.