What are the hardware requirements for NeoHorse 1 9B?

NeoHorse 1 9B requires approximately 18 GB of VRAM and supports a context window of 256K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed NeoHorse 1 9B and how large is it?

NeoHorse 1 9B is developed by TokenRhythm, a model with 9b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate NeoHorse 1 9B?

NeoHorse 1 9B is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

NeoHorse 1 9B by TokenRhythm — VRAM 18GB, 256K context

Name: NeoHorse 1 9B
Author: TokenRhythm

NeoHorse 1 9B is an open-source language model by TokenRhythm. Features: 9b LLM, VRAM: 18GB, Context: 256K, License: apache-2.0, Instruction-Based, LLM Explorer Score: 0.38.

Arxiv:2609.08183 Agentic Base model:finetune:qwen/qwen3... Base model:qwen/qwen3.5-9b Coding Conversational Endpoints compatible Instruct Instruction-following Qwen3 5 text Reasoning Region:us Safetensors Sharded Tensorflow Tool-use

Model Card on HF 🤗: https://huggingface.co/TokenRhythm/NeoHorse-1-9B

NeoHorse 1 9B Parameters and Internals

LLM Name	NeoHorse 1 9B
Repository 🤗	https://huggingface.co/TokenRhythm/NeoHorse-1-9B
Base Model(s)	Qwen/Qwen3.5-9B Qwen/Qwen3.5-9B
Model Size	9b
Required VRAM	18 GB
Updated	2026-09-09
Maintainer	TokenRhythm
Model Type	qwen3_5_text
Instruction-Based	Yes
Model Files	5.0 GB: 1-of-4 5.0 GB: 2-of-4 5.0 GB: 3-of-4 3.0 GB: 4-of-4
Model Architecture	Qwen3_5ForCausalLM
License	apache-2.0
Context Length	262144
Model Max Length	262144
Transformers Version	5.16.1
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|endoftext\|>
Vocabulary Size	248320
Errors	replace

Rank the NeoHorse 1 9B capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation

Best Alternatives to NeoHorse 1 9B

Best Alternatives	Context / RAM	Downloads	Likes
FlashModel Qwen3.5 9B	256K / 17.9 GB	325	0
NeoHorse 1 9B FP8 Calibrated	256K / 11 GB	27	1
Nyx RP 9B Instruct 2608 V1	256K / 18.4 GB	3167	5