Instructions to use Amalgafy/Qwen3-Coder-30B-A3B-Instruct-MER-Q4-0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use Amalgafy/Qwen3-Coder-30B-A3B-Instruct-MER-Q4-0 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 Amalgafy/Qwen3-Coder-30B-A3B-Instruct-MER-Q4-0:Q4_0
# Run inference directly in the terminal:
llama cli -hf Amalgafy/Qwen3-Coder-30B-A3B-Instruct-MER-Q4-0:Q4_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Amalgafy/Qwen3-Coder-30B-A3B-Instruct-MER-Q4-0:Q4_0
# Run inference directly in the terminal:
llama cli -hf Amalgafy/Qwen3-Coder-30B-A3B-Instruct-MER-Q4-0:Q4_0

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 Amalgafy/Qwen3-Coder-30B-A3B-Instruct-MER-Q4-0:Q4_0
# Run inference directly in the terminal:
./llama-cli -hf Amalgafy/Qwen3-Coder-30B-A3B-Instruct-MER-Q4-0:Q4_0

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 Amalgafy/Qwen3-Coder-30B-A3B-Instruct-MER-Q4-0:Q4_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Amalgafy/Qwen3-Coder-30B-A3B-Instruct-MER-Q4-0:Q4_0

Use Docker

docker model run hf.co/Amalgafy/Qwen3-Coder-30B-A3B-Instruct-MER-Q4-0:Q4_0

LM Studio
Jan
Ollama
How to use Amalgafy/Qwen3-Coder-30B-A3B-Instruct-MER-Q4-0 with Ollama:
```
ollama run hf.co/Amalgafy/Qwen3-Coder-30B-A3B-Instruct-MER-Q4-0:Q4_0
```

Unsloth Studio

How to use Amalgafy/Qwen3-Coder-30B-A3B-Instruct-MER-Q4-0 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 Amalgafy/Qwen3-Coder-30B-A3B-Instruct-MER-Q4-0 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 Amalgafy/Qwen3-Coder-30B-A3B-Instruct-MER-Q4-0 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Amalgafy/Qwen3-Coder-30B-A3B-Instruct-MER-Q4-0 to start chatting

How to use Amalgafy/Qwen3-Coder-30B-A3B-Instruct-MER-Q4-0 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Amalgafy/Qwen3-Coder-30B-A3B-Instruct-MER-Q4-0:Q4_0

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": "Amalgafy/Qwen3-Coder-30B-A3B-Instruct-MER-Q4-0:Q4_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use Amalgafy/Qwen3-Coder-30B-A3B-Instruct-MER-Q4-0 with Docker Model Runner:
```
docker model run hf.co/Amalgafy/Qwen3-Coder-30B-A3B-Instruct-MER-Q4-0:Q4_0
```

Lemonade

How to use Amalgafy/Qwen3-Coder-30B-A3B-Instruct-MER-Q4-0 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Amalgafy/Qwen3-Coder-30B-A3B-Instruct-MER-Q4-0:Q4_0

Run and chat with the model

lemonade run user.Qwen3-Coder-30B-A3B-Instruct-MER-Q4-0-Q4_0

List all available models

lemonade list

Hermes Agent

How to use Amalgafy/Qwen3-Coder-30B-A3B-Instruct-MER-Q4-0 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Amalgafy/Qwen3-Coder-30B-A3B-Instruct-MER-Q4-0:Q4_0

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 Amalgafy/Qwen3-Coder-30B-A3B-Instruct-MER-Q4-0:Q4_0

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Amalgafy/Qwen3-Coder-30B-A3B-Instruct-MER-Q4-0 with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Amalgafy/Qwen3-Coder-30B-A3B-Instruct-MER-Q4-0:Q4_0

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 "Amalgafy/Qwen3-Coder-30B-A3B-Instruct-MER-Q4-0:Q4_0" \
  --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"

Qwen3-Coder 30B-A3B — MER Q4_0 Qualification Artifact

Private engineering artifact containing the exact Q4_0 files used to qualify Micro-Expert-Router-SSD-Streamed-MoE (MER).

This is not yet a release-grade Amalgafy quantization or model-quality benchmark. The GGUF was requantized from an existing quantized GGUF with llama.cpp using --allow-requantize and --pure. Requantization may compound quantization error.

Artifacts

artifacts/gguf/Qwen3-Coder-30B-A3B-Instruct-pure-Q4_0.gguf
artifacts/mer/qwen3-coder-30b-a3b-mer-q4_0-v1.tar.zst
evidence/pr6-q4-parity.json

The MER archive contains 6,144 routed experts, 435 dense tensors, tokenizer, configuration, metadata, and the canonical ggml-standard-v1 Q4_0 layout.

Qualification

Qualified on an NVIDIA L4 through WGPU/Vulkan using MER commit:

dac1d213cf641ba79a48e74c24f80bc2eca66548

Results:

Seven raw WGSL Q4_0 cases passed
Three complete checkpoint-expert vectors passed
Initial expert installation occurred exactly once
Subsequent vectors uploaded zero expert-weight bytes
Zero CPU fallback or degraded expert execution
Worst complete-expert absolute error: 7.6293945e-06

Checksums

Pure Q4_0 GGUF: 8ddf61cadd354a5095905cc5ce535c44b777d0313ac241abcd2ceafa3362551b
MER archive: 659b8d31d0a83292c632aa109c8edb5301f4041b1a60ef43c6f23ec0404061fe
Parity report: 1d579a9e7ebc93191544ff162027e840dfbbd55ae7cc85e81021bb6e85784c60

Provenance

Upstream: Qwen/Qwen3-Coder-30B-A3B-Instruct
License: Apache-2.0
llama.cpp: 030ebb558a5820b444a8f836ed5cdd46c9b4bd7a
MER: dac1d213cf641ba79a48e74c24f80bc2eca66548

Qwen3-Coder is provided by the Qwen team. This repository preserves the upstream license and identifies the conversion and requantization changes.

Downloads last month: 47

GGUF

Model size

31B params

Architecture

qwen3moe

Hardware compatibility

4-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for Amalgafy/Qwen3-Coder-30B-A3B-Instruct-MER-Q4-0

Base model

Qwen/Qwen3-Coder-30B-A3B-Instruct

Quantized

(164)

this model