Instructions to use Abiray/ZAYA1-8B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Abiray/ZAYA1-8B-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Abiray/ZAYA1-8B-GGUF",
	filename="ZAYA1-8B-Q3_K_M.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use Abiray/ZAYA1-8B-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Abiray/ZAYA1-8B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf Abiray/ZAYA1-8B-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Abiray/ZAYA1-8B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf Abiray/ZAYA1-8B-GGUF:Q4_K_M

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 Abiray/ZAYA1-8B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Abiray/ZAYA1-8B-GGUF:Q4_K_M

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 Abiray/ZAYA1-8B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Abiray/ZAYA1-8B-GGUF:Q4_K_M

Use Docker

docker model run hf.co/Abiray/ZAYA1-8B-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use Abiray/ZAYA1-8B-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Abiray/ZAYA1-8B-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Abiray/ZAYA1-8B-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Abiray/ZAYA1-8B-GGUF:Q4_K_M

Ollama
How to use Abiray/ZAYA1-8B-GGUF with Ollama:
```
ollama run hf.co/Abiray/ZAYA1-8B-GGUF:Q4_K_M
```

Unsloth Studio new

How to use Abiray/ZAYA1-8B-GGUF with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for Abiray/ZAYA1-8B-GGUF to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for Abiray/ZAYA1-8B-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Abiray/ZAYA1-8B-GGUF to start chatting

Pi new

How to use Abiray/ZAYA1-8B-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf Abiray/ZAYA1-8B-GGUF:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "Abiray/ZAYA1-8B-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use Abiray/ZAYA1-8B-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf Abiray/ZAYA1-8B-GGUF:Q4_K_M

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 Abiray/ZAYA1-8B-GGUF:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use Abiray/ZAYA1-8B-GGUF with Docker Model Runner:
```
docker model run hf.co/Abiray/ZAYA1-8B-GGUF:Q4_K_M
```

Lemonade

How to use Abiray/ZAYA1-8B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Abiray/ZAYA1-8B-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.ZAYA1-8B-GGUF-Q4_K_M

List all available models

lemonade list

ZAYA1-8B GGUF Quantizations

This repository contains GGUF quantizations of Zyphra/ZAYA1-8B.

⚠️ CRITICAL USAGE NOTE: The zaya architecture (which utilizes a unique Compressed Convolutional Attention mechanism and an MLP router) is currently undergoing experimental integration into llama.cpp. These quantizations were generated using the bleeding-edge Draft PR #23112. To protect the model's complex reasoning and routing logic, the highly sensitive cca_conv_grp layers were explicitly excluded from quantization and remain in higher precision.

To run these models, you must compile llama.cpp locally from that specific PR branch until official support is merged into the master branch.

Model Details

ZAYA1-8B is a frontier-level reasoning Mixture-of-Experts (MoE) model designed for high intelligence density and local deployment.

Total Parameters: ~8.4B
Active Parameters (per token): ~760M
Architecture: zaya (Sparse MoE)
License: Apache-2.0
Creator: Zyphra

Available Quants

Format	File Size	Description
Q3_K_M	4.51 GB	Smallest viable quant. Heavy compression, potential logic degradation.
Q4_K_S	5.26 GB	Very small. High compression, suitable for strict VRAM limits.
Q4_K_M	5.57 GB	Recommended. The sweet spot for balancing VRAM usage and reasoning capabilities.
Q5_K_M	6.43 GB	High precision. Great if you have slightly more RAM/VRAM to spare.
Q6_K	7.35 GB	Very high precision. Near uncompressed performance.
Q8_0	9.49 GB	Maximum precision quant. Negligible intelligence loss.

How to Run (Experimental)

Since standard llama.cpp releases do not yet recognize the zaya metadata keys, you must fetch the working pull request to run these files:

# Clone the main repository
git clone [https://github.com/ggerganov/llama.cpp.git](https://github.com/ggerganov/llama.cpp.git)
cd llama.cpp

# Fetch the specific Draft PR that contains working ZAYA inference
git fetch origin pull/23112/head:zaya-working-pr
git checkout zaya-working-pr

# Build with CUDA support (Recommended)
cmake -B build -DGGML_CUDA=ON
cmake --build build --config Release -j 8

# Run the model
./build/bin/llama-cli -m /path/to/ZAYA1-8B-Q4_K_M.gguf -p "Your complex reasoning prompt here" -ngl 99 -c 4096 -n 512

Downloads last month: 6,513

GGUF

Model size

9B params

Architecture

zaya

Hardware compatibility

3-bit

4-bit

5-bit

6-bit

8-bit

Model tree for Abiray/ZAYA1-8B-GGUF

Base model

Zyphra/ZAYA1-base

Finetuned

Zyphra/ZAYA1-reasoning-base

Finetuned

Zyphra/ZAYA1-8B

Quantized

(14)

this model

Abiray
/

ZAYA1-8B-GGUF

ZAYA1-8B GGUF Quantizations

Model Details

Available Quants

How to Run (Experimental)

Model tree for Abiray/ZAYA1-8B-GGUF

Space using Abiray/ZAYA1-8B-GGUF 1