Instructions to use CodeFault/Qwen3-Coder-Next-64B-REAP-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use CodeFault/Qwen3-Coder-Next-64B-REAP-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="CodeFault/Qwen3-Coder-Next-64B-REAP-GGUF",
	filename="qwen3-coder-next-64b-REAP-Q4_K_M.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use CodeFault/Qwen3-Coder-Next-64B-REAP-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 CodeFault/Qwen3-Coder-Next-64B-REAP-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf CodeFault/Qwen3-Coder-Next-64B-REAP-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf CodeFault/Qwen3-Coder-Next-64B-REAP-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf CodeFault/Qwen3-Coder-Next-64B-REAP-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 CodeFault/Qwen3-Coder-Next-64B-REAP-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf CodeFault/Qwen3-Coder-Next-64B-REAP-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 CodeFault/Qwen3-Coder-Next-64B-REAP-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf CodeFault/Qwen3-Coder-Next-64B-REAP-GGUF:Q4_K_M

Use Docker

docker model run hf.co/CodeFault/Qwen3-Coder-Next-64B-REAP-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use CodeFault/Qwen3-Coder-Next-64B-REAP-GGUF with Ollama:
```
ollama run hf.co/CodeFault/Qwen3-Coder-Next-64B-REAP-GGUF:Q4_K_M
```

Unsloth Studio

How to use CodeFault/Qwen3-Coder-Next-64B-REAP-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 CodeFault/Qwen3-Coder-Next-64B-REAP-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 CodeFault/Qwen3-Coder-Next-64B-REAP-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for CodeFault/Qwen3-Coder-Next-64B-REAP-GGUF to start chatting

How to use CodeFault/Qwen3-Coder-Next-64B-REAP-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf CodeFault/Qwen3-Coder-Next-64B-REAP-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": "CodeFault/Qwen3-Coder-Next-64B-REAP-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use CodeFault/Qwen3-Coder-Next-64B-REAP-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 CodeFault/Qwen3-Coder-Next-64B-REAP-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 CodeFault/Qwen3-Coder-Next-64B-REAP-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use CodeFault/Qwen3-Coder-Next-64B-REAP-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf CodeFault/Qwen3-Coder-Next-64B-REAP-GGUF:Q4_K_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 "CodeFault/Qwen3-Coder-Next-64B-REAP-GGUF:Q4_K_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 CodeFault/Qwen3-Coder-Next-64B-REAP-GGUF with Docker Model Runner:
```
docker model run hf.co/CodeFault/Qwen3-Coder-Next-64B-REAP-GGUF:Q4_K_M
```

Lemonade

How to use CodeFault/Qwen3-Coder-Next-64B-REAP-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull CodeFault/Qwen3-Coder-Next-64B-REAP-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Qwen3-Coder-Next-64B-REAP-GGUF-Q4_K_M

List all available models

lemonade list

Qwen3-Coder-Next-64B-REAP-GGUF / README.md

CodeFault

Update README.md

de09191 verified 3 months ago

preview code

Raw

History Blame Contribute Delete

1.38 kB

metadata

base_model: 0xSero/qwen3-coder-next-64b-REAP
base_model_relation: quantized
language:
  - en
license: apache-2.0
tags:
  - quantized
  - gguf
  - qwen3
  - moe

Qwen3-Coder-Next 64B REAP - GGUF

Quantized GGUF versions of 0xSero/qwen3-coder-next-64b-REAP. These were generated using the default settings with llama-quantize (b8740).

Quantizations provided

File	Quantization	Size
`qwen3-coder-next-64b-REAP-Q4_K_M.gguf`	Q4_K_M	39.1 GB
`qwen3-coder-next-64b-REAP-Q5_K_M.gguf`	Q5_K_M	45.8 GB
`qwen3-coder-next-64b-REAP-Q6_K.gguf`	Q6_K	52.9 GB
`qwen3-coder-next-64b-REAP-Q8_0.gguf`	Q8_0	68.4 GB

Perplexity test

I tested perplexity using llama-perplexity and Salesforce's wikitext-2-raw-v1.

File	Quantization	Ctx	PPL
`qwen3-coder-next-64b-REAP-Q4_K_M.gguf`	Q4_K_M	512	12.6123 +/- 0.10518
`qwen3-coder-next-64b-REAP-Q5_K_M.gguf`	Q5_K_M	512	12.5573 +/- 0.10461
`qwen3-coder-next-64b-REAP-Q6_K.gguf`	Q6_K	512	12.4087 +/- 0.10285
`qwen3-coder-next-64b-REAP-Q8_0.gguf`	Q8_0	512	12.4389 +/- 0.10323
`qwen3-coder-next-64b-REAP-BF16.gguf`	BF16	512	12.4162 +/- 0.10302