Instructions to use alphaZimuth/Hy-MT2-30B-A3B-APEX-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use alphaZimuth/Hy-MT2-30B-A3B-APEX-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="alphaZimuth/Hy-MT2-30B-A3B-APEX-GGUF",
	filename="Hy-MT2-30B-A3B-APEX-I-Balanced.gguf",
)

llm.create_chat_completion(
	messages = "\"Меня зовут Вольфганг и я живу в Берлине\""
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use alphaZimuth/Hy-MT2-30B-A3B-APEX-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 alphaZimuth/Hy-MT2-30B-A3B-APEX-GGUF
# Run inference directly in the terminal:
llama cli -hf alphaZimuth/Hy-MT2-30B-A3B-APEX-GGUF

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf alphaZimuth/Hy-MT2-30B-A3B-APEX-GGUF
# Run inference directly in the terminal:
llama cli -hf alphaZimuth/Hy-MT2-30B-A3B-APEX-GGUF

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 alphaZimuth/Hy-MT2-30B-A3B-APEX-GGUF
# Run inference directly in the terminal:
./llama-cli -hf alphaZimuth/Hy-MT2-30B-A3B-APEX-GGUF

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 alphaZimuth/Hy-MT2-30B-A3B-APEX-GGUF
# Run inference directly in the terminal:
./build/bin/llama-cli -hf alphaZimuth/Hy-MT2-30B-A3B-APEX-GGUF

Use Docker

docker model run hf.co/alphaZimuth/Hy-MT2-30B-A3B-APEX-GGUF

LM Studio
Jan
Ollama
How to use alphaZimuth/Hy-MT2-30B-A3B-APEX-GGUF with Ollama:
```
ollama run hf.co/alphaZimuth/Hy-MT2-30B-A3B-APEX-GGUF
```

Unsloth Studio

How to use alphaZimuth/Hy-MT2-30B-A3B-APEX-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 alphaZimuth/Hy-MT2-30B-A3B-APEX-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 alphaZimuth/Hy-MT2-30B-A3B-APEX-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for alphaZimuth/Hy-MT2-30B-A3B-APEX-GGUF to start chatting

How to use alphaZimuth/Hy-MT2-30B-A3B-APEX-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf alphaZimuth/Hy-MT2-30B-A3B-APEX-GGUF

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": "alphaZimuth/Hy-MT2-30B-A3B-APEX-GGUF"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use alphaZimuth/Hy-MT2-30B-A3B-APEX-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 alphaZimuth/Hy-MT2-30B-A3B-APEX-GGUF

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 alphaZimuth/Hy-MT2-30B-A3B-APEX-GGUF

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use alphaZimuth/Hy-MT2-30B-A3B-APEX-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf alphaZimuth/Hy-MT2-30B-A3B-APEX-GGUF

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 "alphaZimuth/Hy-MT2-30B-A3B-APEX-GGUF" \
  --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 alphaZimuth/Hy-MT2-30B-A3B-APEX-GGUF with Docker Model Runner:
```
docker model run hf.co/alphaZimuth/Hy-MT2-30B-A3B-APEX-GGUF
```

Lemonade

How to use alphaZimuth/Hy-MT2-30B-A3B-APEX-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull alphaZimuth/Hy-MT2-30B-A3B-APEX-GGUF

Run and chat with the model

lemonade run user.Hy-MT2-30B-A3B-APEX-GGUF-{{QUANT_TAG}}

List all available models

lemonade list

Hy-MT2-30B-A3B-APEX-GGUF

GGUF quantizations of Tencent Hy-MT2-30B-A3B using APEX quantization.

This repository provides three APEX quantization variants optimized for different deployment scenarios, quantized by alphaZimuth.

Changelog

2026-7-14
Initial APEX quantization release.
2026-7-15
Fixed hy_v3 architecture compatibility issue and added support for upstream llama.cpp b9993+.
2026-7-18
Added APEX-Imatrix-I series with importance matrix calibration. Added Nano variant for lower memory devices.

Recommended Versions

The APEX-Imatrix-I series is the recommended version of this repository.

Compared with the original APEX quantizations, these models were calibrated with an importance matrix (imatrix.dat) generated from a multilingual translation-focused calibration dataset.

The calibration process achieved: PPL = 2.1519 +/- 0.00207

In practical testing, the Imatrix-calibrated versions consistently provide better translation quality and output stability compared with the non-calibrated versions.

The evaluation was conducted through parallel translation comparisons using the same test samples, with both calibrated and non-calibrated versions compared side by side.

Several advanced LLM-based evaluators, including GLM, DeepSeek, GPT, Qwen, and LongCat, were used to assess the translation results from multiple perspectives. Across these evaluations, the Imatrix-calibrated versions were consistently rated higher for translation accuracy, fluency, and overall output quality.

The original APEX-I series is kept for archival and comparison purposes.

Available Quantizations

Recommended: APEX-Imatrix-I Series

File	Size	Description
`Hy-MT2-30B-A3B-APEX-Imatrix-I-Nano.gguf`	11.5 GB	Lightweight variant for lower-memory devices while maintaining strong translation performance
`Hy-MT2-30B-A3B-APEX-Imatrix-I-Compact.gguf`	14.0 GB	Optimized quality-to-size ratio, ideal for limited VRAM devices
`Hy-MT2-30B-A3B-APEX-Imatrix-I-Quality.gguf`	19.0 GB	Quality-focused variant with higher precision retention
`Hy-MT2-30B-A3B-APEX-Imatrix-I-Balanced.gguf`	20.8 GB	Balanced APEX tier for users prioritizing overall quality

Legacy: Original APEX-I Series

The following versions are preserved for archival purposes:

File	Size	Description
`Hy-MT2-30B-A3B-APEX-I-Compact.gguf`	14.0 GB	Original non-imatrix quantization
`Hy-MT2-30B-A3B-APEX-I-Quality.gguf`	19.0 GB	Original non-imatrix quantization
`Hy-MT2-30B-A3B-APEX-I-Balanced.gguf`	20.8 GB	Original non-imatrix quantization

Quantization Details

Quantized with APEX (based on llama.cpp).

Project: https://github.com/localai-org/apex-quant

Conversion pipeline:

Tencent Hy-MT2-30B-A3B (BF16)
        ↓
convert_hf_to_gguf.py (hy3-port branch)
        ↓
Hy-MT2-30B-A3B-BF16.gguf
        ↓
APEX quantization (with imatrix)
        ↓
APEX GGUF files

Note:

These quantizations were generated with imatrix calibration.
The filenames follow APEX tier naming.

llama.cpp Compatibility

Important

Hy-MT2-30B-A3B uses the hy_v3 architecture.

Support for hy_v3 has been merged into upstream llama.cpp starting from build b9993.

Please use llama.cpp build b9993 or later for inference.

Related upstream PR:

https://github.com/ggml-org/llama.cpp/pull/25395

Usage

Example:

llama-cli \
-m Hy-MT2-30B-A3B-APEX-Imatrix-I-Compact.gguf \
-p "Translate the following sentence into Chinese: Hello world"

Benchmark

Test Environment

CPU: Intel Core i7-12700H
GPU: NVIDIA RTX 3060 Laptop GPU 12GB
RAM: 24GB

Software:

llama.cpp build: b10056
CUDA backend

Settings:

-ngl 99
-b 2048
-ub 2048
-t 12

Optimized --n-cpu-moe values on RTX3060 12GB were used for each quantization.

Quantization	Size	n_cpu_moe	PP512	TG128
`APEX-Imatrix-I-Nano`	11.59 GiB	4	1224.25 tok/s	71.92 tok/s
`APEX-Imatrix-I-Compact`	14.00 GiB	13	835.57 tok/s	56.16 tok/s
`APEX-Imatrix-I-Quality`	19.05 GiB	25	520.03 tok/s	33.49 tok/s
`APEX-Imatrix-I-Balanced`	20.81 GiB	26	463.11 tok/s	28.93 tok/s

Credits

Tencent Hy-MT2 team for the original model.
LocalAI team for the APEX quantization framework.
llama.cpp contributors for GGUF support.
gigass03 for identifying the hy_v3 architecture metadata compatibility issue and verifying the fix.

License

Apache-2.0

Downloads last month: 5,970

GGUF

Model size

30B params

Architecture

hy_v3

Hardware compatibility

We're not able to determine the quantization variants.

View all variants