# TokenRhythm/NeoHorse

> The NeoHorse family of open-weight models for agent workflows: NeoHorse-1 (4B and 9B) for tool use, coding, and instruction following, and NeoHorse-Jev-4B which turns application state into structured decisions via prefill-only inference.

- Magnitude: 2.0 out of 10 — Steady
- Stars: 947 total · +0 stars today, ≈ 44 by evening
- Star trust: star growth looks organic
- Category: Language models · Language: Python · License: Apache-2.0 · Created: 2026-09-04 · Last push: 2026-09-24
- GitHub: https://github.com/TokenRhythm/NeoHorse · Page: https://gitnova.dev/en/r/TokenRhythm/NeoHorse

## Useful for

- Run NeoHorse-1-4B locally in GGUF quantization for agent tasks without cloud
- Use NeoHorse-Jev-4B to pick a tool or route a request based on application state
- Post-train the model for your own harness via routing-guided agentic post-training

## Why it’s here

- 0 stars so far today, about 44 expected by the end of the day.
- The repository is 21 days old and already has 947 stars.
- Top new repositories this month: #100.

## Star trust

Star growth looks organic.
- Fewer forks than usual: 11 for 947 stars.

Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer.

## Numbers

- Forks: 11
- Issues and pull requests: 2
- Watchers: 1
- Average over the last week: 58 per day
- Usual pace: 36 per day
- Stars in the last hour (measured): 4

## Stars per day, last 27 days (oldest → newest, today is partial)

2026-08-30 … 2026-09-25: 0, 0, 0, 0, 0, 0, 0, 6, 9, 32, 57, 22, 32, 39, 53, 121, 60, 45, 57, 55, 63, 56, 62, 68, 51, 61, 0

## Spotted in now

- Top new repositories this month: #100

## More in this category

1. **jaredpalmer/kev** — 6.5 · Peaking · Language models · Python · +0 stars today, ≈ 353 by evening
   kev is a LoRA adapter with a small readout head on top of Qwen2.5-0.5B that answers many typed questions about a document in a single forward pass, returning calibrated probabilities instead of text.
   Full card: https://gitnova.dev/en/r/jaredpalmer/kev.md
2. **deepopen-com/deepopen** — 5.9 · Early signal · Language models · Python · +0 stars today, ≈ 195 by evening
   Open-source non-autoregressive System 1 decision engine for typed decisions: returns typed answers (choice, score, noul) in a single forward pass across 100+ languages without generating text. Suited for classification, routing and…
   Full card: https://gitnova.dev/en/r/deepopen-com/deepopen.md
3. **togethercomputer/tev1** — 5.7 · Early signal · Language models · Python · +0 stars today, ≈ 56 by evening
   Open dataset and fine-tuning recipe for Qwen3.5-4B that picks one of 2–24 options given context and a question. The repo ships data, build scripts, Together AI training and evaluation tooling.
   Full card: https://gitnova.dev/en/r/togethercomputer/tev1.md
4. **NVIDIA/Model-Optimizer** — 5.2 · Breakout · Language models · Python · +0 stars today, ≈ 184 by evening
   NVIDIA library for compressing and accelerating models: quantization, pruning, distillation, NAS and speculative decoding with export to TensorRT-LLM, vLLM, SGLang. For ML engineers preparing models for deployment.
   Full card: https://gitnova.dev/en/r/NVIDIA/Model-Optimizer.md
5. **Liuziyu77/Valen** — 4.7 · Early signal · Language models · Python · +0 stars today, ≈ 39 by evening
   A multimodal decision model built on a Qwen3.5-0.8B/2B backbone: it takes text, images and video with an instruction and returns probabilities over supplied candidates without generating answer tokens. The repo includes model code, data…
   Full card: https://gitnova.dev/en/r/Liuziyu77/Valen.md

---

Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score.
Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast.
Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself.
Data as of 2026-09-25 03:35 UTC, updated every 30 minutes.