DEDUPED Hot AI repos, turned into use cases Get 5 a day

What you can do with Neo Horse

NeoHorse is an open-weight model family from TokenRhythm for agent workflows, with 4B and 9B text models for tool use, coding, and instruction following, plus a 4B decision model called NeoHorse-Jev.

Trended earlier

TokenRhythm/NeoHorse on GitHub

Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk.

What do you want to do?

4 use cases

  • Serve NeoHorse-1 locally for agent tool calls

    Host NeoHorse-1-4B on your own GPU with vLLM and send it chat requests from a local script.

    View prompt
    In the TokenRhythm/NeoHorse repo, follow the vLLM steps in the Deployment section to serve the NeoHorse-1-4B checkpoint at <model-directory> on port 8000 with served name neohorse-1-4B. Return the chat reply text for the prompt <test-prompt>. Verify that the server log shows the model loaded without errors before sending the request.

  • Route requests with NeoHorse-Jev structured decisions

    Use NeoHorse-Jev-4B to pick an action, check a condition, or assign a rating from app state.

    View prompt
    In the TokenRhythm/NeoHorse repo, read the NeoHorse-Jev deployment guide in jev/README.md and set up the model bundle at <model-directory>. Send the application state <sample-state> with the Choice question <question> and report the selected answer and its probability. Verify that the probabilities for the listed answers sum to a value you can explain.

  • Run a quantized NeoHorse-1 on your own hardware

    Download a GGUF or MLX build of NeoHorse-1 that uses less memory than BF16 weights.

    View prompt
    In the TokenRhythm/NeoHorse repo, find the GGUF build of NeoHorse-1-4B on Hugging Face at <model-page> and pick the 4-bit quantized file. Follow that model card's deployment instructions and return the model's reply to the prompt <test-prompt>. Verify that the file size of the chosen build is smaller than the 16-bit BF16 build.

  • Rerun NeoHorse-1 with the reported sampling settings

    Serve a NeoHorse-1 checkpoint with the exact SGLang settings listed for the technical report.

    View prompt
    In the TokenRhythm/NeoHorse repo, serve the NeoHorse-1-9B checkpoint at <model-directory> with SGLang v0.5.17 on port 30000 using the reported protocol settings in the Evaluation section. Send the benchmark prompt <benchmark-item> and return the answer and the settings used. Verify that the request sets temperature=1.0, top_p=0.95, and top_k=20 before recording any score.

How to use Neo Horse

  1. Check you have what it needs: A machine with enough GPU memory for the 4B or 9B BF16 weights, or a quantized GGUF or MLX build for smaller hardware; Python with pip available; Disk space for the downloaded checkpoint from Hugging Face or ModelScope.
  2. Open TokenRhythm/NeoHorse on GitHub and read the README and license.
  3. Download NeoHorse-1-4B from Hugging Face or ModelScope to a local directory that contains config.json, tokenizer files, and weights.
  4. Run pip install -U vllm
  5. Set MODEL_PATH to that directory, then run vllm serve "$MODEL_PATH" --served-model-name neohorse-1-4B --host 0.0.0.0 --port 8000 --max-model-len 262144 --reasoning-parser qwen3 --enable-auto-tool-choice --tool-call-parser qwen3_coder (inferred, check the README)
  6. Run pip install requests

These steps come from our top use case, Serve NeoHorse-1 locally for agent tool calls, which also has a copy-paste agent prompt.

Neo Horse alternatives · Best AI repos for Software and DevOps

About this repo

Requirements

  • A machine with enough GPU memory for the 4B or 9B BF16 weights, or a quantized GGUF or MLX build for smaller hardware
  • Python with pip available
  • Disk space for the downloaded checkpoint from Hugging Face or ModelScope
Maintain Neo Horse? Add the Featured on Deduped badge

Paste this into your README:

[![Featured on Deduped](https://dedupedai.com/badge/tokenrhythm-neohorse.svg)](https://dedupedai.com/use-cases/tokenrhythm-neohorse/?ref=badge)

More badge styles and HTML

Questions about Neo Horse

What is Neo Horse?

NeoHorse is an open-weight model family from TokenRhythm for agent workflows, with 4B and 9B text models for tool use, coding, and instruction following, plus a 4B decision model called NeoHorse-Jev. It is an open-source project on GitHub: https://github.com/TokenRhythm/NeoHorse.

Who is Neo Horse for?

Developers and teams who want to run open-weight agent or decision models on their own hardware or serving stack.

What can I do with Neo Horse?

4 use cases so far, for example: Serve NeoHorse-1 locally for agent tool calls; Route requests with NeoHorse-Jev structured decisions; Run a quantized NeoHorse-1 on your own hardware. Each has steps and a copy-paste agent prompt.

What do I need to run Neo Horse?

A machine with enough GPU memory for the 4B or 9B BF16 weights, or a quantized GGUF or MLX build for smaller hardware; Python with pip available; Disk space for the downloaded checkpoint from Hugging Face or ModelScope.

What are alternatives to Neo Horse?

Other hot AI repos in Software and DevOps: Harness2, iFixAi, Orca, Diagram Design, AI Memory.

Is Neo Horse safe to run?

Deduped does not own, audit or vouch for it. Read the README and license, run it on your own systems first and review every command before you run it.