# NeoHorse-1-4B tunes Qwen3.5 for agentic work

> A compact 4-billion-parameter model built for tool use, coding, and multi-step reasoning arrives from TokenRhythm.

Published by The Open Weights on Sep 5, 2026. Canonical: https://theopenweights.com/news/neohorse-1-4b-2c8n

## Key facts

- Company: TokenRhythm
- Model: NeoHorse-1-9B
- Version: 1-4B
- Category: Text / LLM
- Modalities: Text / LLM, Code, Reasoning
- License: Other (Open weights, commercial use allowed)
- Parameters: 4B
- Context window: 262K tokens
- Architecture: Qwen3_5ForCausalLM
- Precision: BF16
- Weights size: 8.4 GB
- Significance: minor
- Published: 2026-09-05
- Last verified: 2026-09-14
- Hugging Face: https://huggingface.co/TokenRhythm/NeoHorse-1-4B
- Canonical URL: https://theopenweights.com/news/neohorse-1-4b-2c8n

TokenRhythm has released [NeoHorse-1-4B](https://huggingface.co/TokenRhythm/NeoHorse-1-4B), a compact language model fine-tuned from Alibaba's Qwen3.5-4B base. At 4 billion parameters, it targets a familiar sweet spot: small enough to run on modest hardware, but tuned specifically for agentic behavior rather than general chat.

The model is aimed at three overlapping tasks — tool use, code generation, and step-by-step reasoning. That framing puts it squarely in the growing category of small models designed to act as the engine inside automated workflows, where a model calls external functions and chains multiple actions together instead of simply answering a single prompt.

## Why it matters

Agentic capability has largely been the domain of larger frontier models, so the appeal of a 4B option is practical:

- Lower memory and compute requirements for local or edge deployment
- Faster inference for latency-sensitive tool-calling loops
- A permissive-enough footprint to experiment without frontier-scale infrastructure

A few caveats are worth noting. The repository lists the license simply as "other," so teams should check the terms before commercial use, and no context-length or benchmark figures accompany this initial release. As a first version from a smaller publisher building atop Qwen, NeoHorse-1-4B is best treated as a candidate to evaluate against established small agentic models rather than a proven drop-in. The full details are on its [Hugging Face page](https://huggingface.co/TokenRhythm/NeoHorse-1-4B).

## Get the model

- [Hugging Face](https://huggingface.co/TokenRhythm/NeoHorse-1-4B)

## Sources

- [TokenRhythm/NeoHorse-1-4B](https://huggingface.co/TokenRhythm/NeoHorse-1-4B) — Hugging Face, Sep 5, 2026

---
Source: The Open Weights (https://theopenweights.com/). Aggregated and written by Claude, curated by humans. Cite as: "NeoHorse-1-4B tunes Qwen3.5 for agentic work", The Open Weights, Sep 5, 2026, https://theopenweights.com/news/neohorse-1-4b-2c8n