Instructions to use devanshbatham/nyx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use devanshbatham/nyx with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf devanshbatham/nyx
# Run inference directly in the terminal:
llama cli -hf devanshbatham/nyx

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf devanshbatham/nyx
# Run inference directly in the terminal:
llama cli -hf devanshbatham/nyx

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf devanshbatham/nyx
# Run inference directly in the terminal:
./llama-cli -hf devanshbatham/nyx

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf devanshbatham/nyx
# Run inference directly in the terminal:
./build/bin/llama-cli -hf devanshbatham/nyx

Use Docker

docker model run hf.co/devanshbatham/nyx

LM Studio
Jan

vLLM

How to use devanshbatham/nyx with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "devanshbatham/nyx"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "devanshbatham/nyx",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/devanshbatham/nyx

Ollama
How to use devanshbatham/nyx with Ollama:
```
ollama run hf.co/devanshbatham/nyx
```
Unsloth Desktop

How to use devanshbatham/nyx with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf devanshbatham/nyx

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "devanshbatham/nyx"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use devanshbatham/nyx with Docker Model Runner:
```
docker model run hf.co/devanshbatham/nyx
```

Lemonade

How to use devanshbatham/nyx with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull devanshbatham/nyx

Run and chat with the model

lemonade run user.nyx-{{QUANT_TAG}}

List all available models

lemonade list

Hermes Agent

How to use devanshbatham/nyx with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf devanshbatham/nyx

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default devanshbatham/nyx

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use devanshbatham/nyx with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf devanshbatham/nyx

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "devanshbatham/nyx" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

nyx

File size: 2,735 Bytes

f80a01b
 
 
 
d0a349e
f80a01b
 
 
d0a349e
 
 
 
f80a01b
 
7519c08
f80a01b
c9150ad
f80a01b
c9150ad
f80a01b
 
 
 
 
c9150ad
d0a349e
c9150ad
 
d0a349e
f80a01b
7519c08
f80a01b
 
d0a349e
47845a3
 
 
 
7519c08
d0a349e
f80a01b
d0a349e
 
 
f80a01b
 
47845a3
7519c08
c9150ad
f80a01b
c9150ad
f80a01b
c9150ad
f80a01b
d0a349e
 
 
 
 
 
 
 
 
 
 
 
39d1566
c9150ad
f80a01b
c9150ad
f80a01b
c9150ad

---
license: apache-2.0
pipeline_tag: text-generation
base_model:
  - Qwen/Qwen3.5-4B
tags:
  - nyx
  - qwen3.5
  - gguf
  - llama-cpp
  - quantized
  - classification
---

# nyx

nyx is a compact 4B decision model for Choice, Score, and Noul workloads. The release is one 3.29 GB GGUF for llama.cpp on CPU, Apple Metal, NVIDIA CUDA, and AMD HIP.

![Animated green-and-white chart comparing nyx and Jev across six classification benchmarks](assets/nyx-benchmarks.svg)

## Model

| Property | Value |
|---|---|
| Base | [Qwen/Qwen3.5-4B](https://huggingface.co/Qwen/Qwen3.5-4B) |
| File | `nyx.gguf` |
| Size | 3.29 GB / 3.06 GiB |
| Format | GGUF, importance-matrix IQ4_XS with selected Q5_K/Q6_K tensors |
| SHA-256 | `39d64fb19863cfc067e2411fcb2a0444113dda13798b15de5617736d91914359` |

## Run

```bash
git clone https://github.com/devanshbatham/nyx.git /opt/nyx

python3 -m venv /opt/nyx/.venv
/opt/nyx/.venv/bin/pip install '/opt/nyx[server]'
/opt/nyx/.venv/bin/hf download devanshbatham/nyx --local-dir /opt/nyx-model

/opt/nyx/scripts/build-llama-cpp.sh /opt/llama.cpp

export LLAMA_SERVER_BIN=/opt/llama.cpp/build/bin/llama-server
export NYX_GGUF_PATH=/opt/nyx-model/nyx.gguf
/opt/nyx/scripts/serve-model.sh
```

Allow 8 GB of free RAM, VRAM, or unified memory and 6 GB of disk for one 4,096-token slot. Python 3.11+, Git, CMake, and a recent C++ compiler are required. Larger contexts and concurrent slots need more memory.

The production API and typed Python/TypeScript clients are in [devanshbatham/nyx](https://github.com/devanshbatham/nyx).

## Benchmarks

Accuracy on 2,277 frozen classification requests:

| Benchmark | Qwen3.5-4B base | nyx reference | Jev 1.13 |
|---|---:|---:|---:|
| AG News | **87.75%** | 85.75% | 86.50% |
| TREC coarse | 86.60% | 84.20% | **93.00%** |
| CoLA | 77.75% | **81.50%** | 77.75% |
| RTE | 84.12% | 88.09% | **91.34%** |
| Emotion | **47.67%** | 46.33% | 47.00% |
| IMDb | 95.75% | 95.75% | **97.00%** |
| Dataset-macro accuracy | 79.94% | 80.27% | **82.10%** |
| Pooled accuracy | 81.42% | 81.51% | **83.62%** |
| Round trip, median / p95 | 54.85 / 67.96 ms | 55.56 / 72.77 ms | 182.33 / 245.12 ms |
| Throughput | 17.44 req/s | 17.15 req/s | 42.43 req/s |

Local Qwen and nyx latency: MI325X, concurrency 1. Jev latency: remote HTTPS, concurrency 8. The published GGUF matched the nyx reference on 98.73% of a separate 1,024-case fidelity set. [Reproduce the nyx/Jev benchmark](https://github.com/devanshbatham/nyx/tree/main/benchmarks).

## License

Apache-2.0. nyx is derived from [Qwen/Qwen3.5-4B](https://huggingface.co/Qwen/Qwen3.5-4B); Qwen and Alibaba Cloud are credited as the original model authors. This project is not affiliated with Qwen, Alibaba Cloud, TypeSafe, or Jev.