Text analysisComputer-use agentsRerankers

CLM (Contrastive Language Model)

An open fast-choice model for agents: it takes a description of a situation and a set of options and returns the probability of each without generating text. It can answer yes or no, pick from a list and give a score on a scale. Actions and state are encoded separately, so action vectors can be computed in advance: by the authors' measurements, with a choice among about a thousand options it is up to 13 times faster than the Jev analogue. After fine-tuning it works as a verifier that picks the best of several solutions of a coding agent (DeepSWE 81.6%, Terminal-Bench 2.1 87.6% by their measurements). It needs Linux, an NVIDIA card and Qwen3-8B in vLLM, and the card language is English.

Developer
Contrastive-LM (per the announcement: Stanford together with NVIDIA), USA
First release
Sep 2026
Latest release
Sep 2026
Sizes
8B (a frozen Qwen3-8B plus two small projection heads)
License
Commercial use allowedApache 2.0
Russian
Not supported
Running
On your own serverNeeds a GPU
Industries
Software development, Customer support, Security
Deploy on your server Hugging Face GitHub

What it does

  • fast choice of an agent's next action from given options
  • checking and ranking several solutions of a coding agent
  • routing requests: department, urgency, a score on a scale

Where it is used

building agents and AI gatewayscustomer supportquality control of coding agents

Hardware requirements

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

Versions

  1. deepswe-clm-heads-8k (проверяющий для кода)
  2. CLM-v0.1-8B

How to run it

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.

Frequently asked questions

Can CLM (Contrastive Language Model) 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 CLM (Contrastive Language Model) need?

At minimum: One GPU with 16–80 GB — mid-size 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 CLM (Contrastive Language Model) support Russian?

No. The developer documentation lists the supported languages and Russian is not among them.

Where can I download CLM (Contrastive Language Model) and what does it cost?

The CLM (Contrastive Language Model) 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

Text analysisJEV и GEVAutoTrust AI · SingaporeCommercial use allowed

Open decision models: for yes/no, pick-one and rate-0-to-5 questions they answer with probabilities in one pass, and can also reason when needed. Not affiliated with the closed Jev from TypeSafe.

DetailsText analysisvLLM Semantic Router: Decision и VelavLLM Semantic Router project · international projectCommercial use allowed

An open family of models for an AI gateway: they answer a request with probabilities without generating text. They detect topic and urgency, jailbreak attempts, harmful requests, personal data and whether a tool is needed. Small versions run on a CPU, Vela understands 17 languages including Russian. The new d3 (27B) also reads several images and videos, and d3-turbo is, by the authors' own estimate, 4 points more accurate on text.

DetailsText analysisLiquid d1Liquid AI · USACommercial use with conditions

Small decision models: from text, an image or a voice clip they answer yes or no, pick an option or give a rating in one pass, without writing text. d1-3B sees images, d1-omni-600M also hears speech up to 30 seconds. Russian is listed.

Details

Source: huggingface.co/Contrastive-LM/CLM-v0.1-8B. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.