Instructions to use AtomicChat/Hy3-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AtomicChat/Hy3-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="AtomicChat/Hy3-GGUF",
	filename="Hy3-IQ1_M.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use AtomicChat/Hy3-GGUF 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 AtomicChat/Hy3-GGUF:IQ1_M
# Run inference directly in the terminal:
llama cli -hf AtomicChat/Hy3-GGUF:IQ1_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf AtomicChat/Hy3-GGUF:IQ1_M
# Run inference directly in the terminal:
llama cli -hf AtomicChat/Hy3-GGUF:IQ1_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 AtomicChat/Hy3-GGUF:IQ1_M
# Run inference directly in the terminal:
./llama-cli -hf AtomicChat/Hy3-GGUF:IQ1_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 AtomicChat/Hy3-GGUF:IQ1_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf AtomicChat/Hy3-GGUF:IQ1_M

Use Docker

docker model run hf.co/AtomicChat/Hy3-GGUF:IQ1_M

LM Studio
Jan

vLLM

How to use AtomicChat/Hy3-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "AtomicChat/Hy3-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": "AtomicChat/Hy3-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/AtomicChat/Hy3-GGUF:IQ1_M

Ollama
How to use AtomicChat/Hy3-GGUF with Ollama:
```
ollama run hf.co/AtomicChat/Hy3-GGUF:IQ1_M
```

Unsloth Studio

How to use AtomicChat/Hy3-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 AtomicChat/Hy3-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 AtomicChat/Hy3-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for AtomicChat/Hy3-GGUF to start chatting

How to use AtomicChat/Hy3-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf AtomicChat/Hy3-GGUF:IQ1_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": "AtomicChat/Hy3-GGUF:IQ1_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use AtomicChat/Hy3-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf AtomicChat/Hy3-GGUF:IQ1_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 AtomicChat/Hy3-GGUF:IQ1_M

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use AtomicChat/Hy3-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf AtomicChat/Hy3-GGUF:IQ1_M

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 "AtomicChat/Hy3-GGUF:IQ1_M" \
  --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"

Docker Model Runner
How to use AtomicChat/Hy3-GGUF with Docker Model Runner:
```
docker model run hf.co/AtomicChat/Hy3-GGUF:IQ1_M
```

Lemonade

How to use AtomicChat/Hy3-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull AtomicChat/Hy3-GGUF:IQ1_M

Run and chat with the model

lemonade run user.Hy3-GGUF-IQ1_M

List all available models

lemonade list

Base model: tencent/Hy3

Hy3 (Tencent Hunyuan Hy3), self-quantized to GGUF by Atomic Chat. Built straight from Tencent's original weights with a per-tensor importance matrix. Runs fully offline, including a 1-bit build that squeezes this 295B model onto a single multi-GPU box.

Highlights

295B-parameter MoE with 21B active (192 experts, top-8) plus a 3.8B MTP layer, so it delivers flagship-scale capability at a fraction of the active compute.
Rivals open-source flagships with 2-5x its parameters, per Tencent, and edges out GLM-5.1 in blind expert evaluation (2.67/4).
Strong agentic and coding scores (Tencent-reported): SWE-Bench Verified 78, GPQA Diamond 90.4, SWE-Bench Pro 57.9.
Production-grade reliability: stable tool calls, hallucination rate down to 5.4%, commonsense errors 12.7%, multi-turn context issues 7.9%.
256K context with grouped-query attention (8 KV heads, head dim 128) and an MTP layer for speculative decoding.
Adjustable reasoning via reasoning_effort (no_think / low / high) for chain-of-thought when a task needs it.
Full imatrix quantization over calibration_datav3, including a 1-bit IQ1_M.

These GGUFs are self-quantized from the original weights, not a repack. The importance matrix keeps low-bit quants closer to the full-precision model.

Always pass --jinja so the Hy3 chat template is applied. Without it the model can emit malformed turns.

Model Overview

Property	Value
Base model	`tencent/Hy3`
Total / active parameters	295B total / 21B active (plus a 3.8B MTP layer)
Layers	80 (plus 1 MTP layer)
Experts	192 experts, top-8 activated
Context length	256K
Architecture	Mixture-of-Experts, GQA (8 KV heads, head dim 128), MTP speculative-decoding layer, reasoning modes
This repo	GGUF quants (imatrix): `Q4_K_M` for near-reference quality, and a 1-bit `IQ1_M` (≈92GB) that makes this 295B model run locally.

Scores are Tencent's published results for the base tencent/Hy3. Quantization preserves the large majority of this; Q4_K_M and up sit within a point or two of full precision.

Choosing a quant

Quant	Size	Notes
`IQ1_M`	91.8 GB	Smallest. 1-bit imatrix build that makes the 295B model run locally (≈92GB, e.g. a 4-GPU box). Expect quality tradeoffs; reasoning still works.
`Q4_K_M`	184.7 GB	Recommended for quality. Near-reference; needs roughly 185GB of combined VRAM and RAM.

Get started

Run Hy3 locally with:

Atomic Chat: the easiest path. Open the app, search AtomicChat/Hy3-GGUF, pick a quant, hit Use this model.
llama.cpp: llama-server -hf AtomicChat/Hy3-GGUF:Q4_K_M --jinja -c 8192
Ollama: ollama run hf.co/AtomicChat/Hy3-GGUF:Q4_K_M
LM Studio / Jan: search the repo id, download any quant.

Best practices

Parameter	Value
temperature	0.9
top_p	1.0

Reasoning is recommended for Hy3. Pass reasoning_effort (high for full chain-of-thought, low, or no_think for direct answers). On hard tasks, running without reasoning can produce truncated or malformed output.

Run in llama.cpp

git clone https://github.com/ggerganov/llama.cpp
cmake llama.cpp -B llama.cpp/build -DBUILD_SHARED_LIBS=OFF -DGGML_CUDA=ON
cmake --build llama.cpp/build --config Release -j --target llama-cli llama-server

./llama.cpp/build/bin/llama-server \
    -hf AtomicChat/Hy3-GGUF:IQ1_M \
    --jinja -ngl 99 -c 8192 -fa on

How these were made

Download tencent/Hy3 (original weights).
Convert to GGUF with a llama.cpp build that supports the Hy3 (hy_v3) architecture and its MTP layer.
Build an importance matrix over calibration_datav3.
Quantize with --imatrix: Q4_K_M for quality and IQ1_M for the smallest footprint that keeps this 295B model coherent.