Instructions to use nerve4/Qwen2.5-Coder-7B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use nerve4/Qwen2.5-Coder-7B-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 nerve4/Qwen2.5-Coder-7B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf nerve4/Qwen2.5-Coder-7B-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 nerve4/Qwen2.5-Coder-7B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf nerve4/Qwen2.5-Coder-7B-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 nerve4/Qwen2.5-Coder-7B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf nerve4/Qwen2.5-Coder-7B-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 nerve4/Qwen2.5-Coder-7B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf nerve4/Qwen2.5-Coder-7B-GGUF:Q4_K_M

Use Docker

docker model run hf.co/nerve4/Qwen2.5-Coder-7B-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use nerve4/Qwen2.5-Coder-7B-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "nerve4/Qwen2.5-Coder-7B-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": "nerve4/Qwen2.5-Coder-7B-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/nerve4/Qwen2.5-Coder-7B-GGUF:Q4_K_M

Ollama
How to use nerve4/Qwen2.5-Coder-7B-GGUF with Ollama:
```
ollama run hf.co/nerve4/Qwen2.5-Coder-7B-GGUF:Q4_K_M
```
Unsloth Desktop

How to use nerve4/Qwen2.5-Coder-7B-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf nerve4/Qwen2.5-Coder-7B-GGUF:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "nerve4/Qwen2.5-Coder-7B-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use nerve4/Qwen2.5-Coder-7B-GGUF with Docker Model Runner:
```
docker model run hf.co/nerve4/Qwen2.5-Coder-7B-GGUF:Q4_K_M
```

Lemonade

How to use nerve4/Qwen2.5-Coder-7B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull nerve4/Qwen2.5-Coder-7B-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Qwen2.5-Coder-7B-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use nerve4/Qwen2.5-Coder-7B-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 nerve4/Qwen2.5-Coder-7B-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 nerve4/Qwen2.5-Coder-7B-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use nerve4/Qwen2.5-Coder-7B-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf nerve4/Qwen2.5-Coder-7B-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 "nerve4/Qwen2.5-Coder-7B-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"

nerve4/Qwen2.5-Coder-7B-GGUF

qwen2.5-coder-7b-q4_k_m.gguf — a Q4_K_M GGUF of Qwen/Qwen2.5-Coder-7B (the base model, for code completion / fill-in-the-middle), built by the Nerve4 project. The upstream publisher provides no GGUF of the base model, so we convert it ourselves from the official weights and publish the result so that Nerve4 can install it.


File	`qwen2.5-coder-7b-q4_k_m.gguf` (4.36 GiB, 4683073376 bytes)
SHA-256	`c1096c17c7f49aff6f82ec4b1ff36b87a52893a4a37e2cf644019e192930dcab`
Source	Qwen/Qwen2.5-Coder-7B @ `0396a76181e127dfc13e5c5ec48a8cee09938b02`
Converted with	llama.cpp `b11518` (`1f8fa52318b594b373e7447a3c2bb36cdba9515f`): `convert_hf_to_gguf.py` → bf16 → `llama-quantize Q4_K_M`
Licence	Apache-2.0 (same as the upstream weights; see `LICENSE` and `NOTICE`)

Verify

sha256sum qwen2.5-coder-7b-q4_k_m.gguf
# c1096c17c7f49aff6f82ec4b1ff36b87a52893a4a37e2cf644019e192930dcab

Nerve4 checks this hash (and the size) before installing or loading the file — a different file is refused.

Reproduce

Every input is pinned: the source weights by commit and per-file hash (qwen2.5-coder-7b-q4_k_m.manifest), the converter and quantizer by llama.cpp commit. In the Nerve4 repository:

bash bench/scripts/build-llamacpp.sh cpu        # tools from the pinned llama.cpp commit
bash bench/scripts/convert-model.sh             # downloads, verifies, converts, quantizes

The script prints the SHA-256 of the result; it should equal the one above.

Changes

Format conversion (safetensors → GGUF) and Q4_K_M quantization only. No fine-tuning, no change to the weights beyond quantization, no change to the tokenizer.

Use

Nerve4 (installs and verifies it for you): POST /n4/v1/models/qwen2.5-coder-7b-q4_k_m/install
llama.cpp: llama-server -m qwen2.5-coder-7b-q4_k_m.gguf — fill-in-the-middle via /infill.

This is a base model: it continues and fills in code; it is not tuned to follow instructions.

Downloads last month: 31

GGUF

Model size

8B params

Architecture

qwen2

Hardware compatibility

4-bit

Model tree for nerve4/Qwen2.5-Coder-7B-GGUF

Base model

Qwen/Qwen2.5-7B

Finetuned

Qwen/Qwen2.5-Coder-7B

Quantized

(50)

this model