Instructions to use BabaK07/Qwen2.5-7B-Instruct-1M-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 BabaK07/Qwen2.5-7B-Instruct-1M-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 BabaK07/Qwen2.5-7B-Instruct-1M-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf BabaK07/Qwen2.5-7B-Instruct-1M-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 BabaK07/Qwen2.5-7B-Instruct-1M-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf BabaK07/Qwen2.5-7B-Instruct-1M-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 BabaK07/Qwen2.5-7B-Instruct-1M-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf BabaK07/Qwen2.5-7B-Instruct-1M-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 BabaK07/Qwen2.5-7B-Instruct-1M-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf BabaK07/Qwen2.5-7B-Instruct-1M-GGUF:Q4_K_M

Use Docker

docker model run hf.co/BabaK07/Qwen2.5-7B-Instruct-1M-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use BabaK07/Qwen2.5-7B-Instruct-1M-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "BabaK07/Qwen2.5-7B-Instruct-1M-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": "BabaK07/Qwen2.5-7B-Instruct-1M-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/BabaK07/Qwen2.5-7B-Instruct-1M-GGUF:Q4_K_M

Ollama
How to use BabaK07/Qwen2.5-7B-Instruct-1M-GGUF with Ollama:
```
ollama run hf.co/BabaK07/Qwen2.5-7B-Instruct-1M-GGUF:Q4_K_M
```
Unsloth Desktop

How to use BabaK07/Qwen2.5-7B-Instruct-1M-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf BabaK07/Qwen2.5-7B-Instruct-1M-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": "BabaK07/Qwen2.5-7B-Instruct-1M-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use BabaK07/Qwen2.5-7B-Instruct-1M-GGUF with Docker Model Runner:
```
docker model run hf.co/BabaK07/Qwen2.5-7B-Instruct-1M-GGUF:Q4_K_M
```

Lemonade

How to use BabaK07/Qwen2.5-7B-Instruct-1M-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull BabaK07/Qwen2.5-7B-Instruct-1M-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Qwen2.5-7B-Instruct-1M-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use BabaK07/Qwen2.5-7B-Instruct-1M-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 BabaK07/Qwen2.5-7B-Instruct-1M-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 BabaK07/Qwen2.5-7B-Instruct-1M-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use BabaK07/Qwen2.5-7B-Instruct-1M-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf BabaK07/Qwen2.5-7B-Instruct-1M-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 "BabaK07/Qwen2.5-7B-Instruct-1M-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"

Qwen2.5 7B Instruct 1M by Qwen

Model creator: Qwen
Original model: Qwen2.5-7B-Instruct-1M

Prompt format

<|im_start|>system
{system_prompt}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant

Download a file (not the whole branch) from below:

Filename	Quant type	File Size	Split	Description
Qwen2.5-7B-Instruct-1M-F32.gguf	f32	30.5 GB	false	Full F32 weights.
Qwen2.5-7B-Instruct-1M-F16.gguf	f16	15.24 GB	false	Full F16 weights.
Qwen2.5-7B-Instruct-1M-Q8_0.gguf	Q8_0	8.10 GB	false	Extremely high quality, generally unneeded but max available quant.
Qwen2.5-7B-Instruct-1M-Q6_K.gguf	Q6_K	6.25 GB	false	Very high quality, near perfect, recommended.
Qwen2.5-7B-Instruct-1M-Q5_K_M.gguf	Q5_K_M	5.44 GB	false	High quality, recommended.
Qwen2.5-7B-Instruct-1M-Q5_K_S.gguf	Q5_K_S	5.32 GB	false	High quality, recommended.
Qwen2.5-7B-Instruct-1M-Q4_1.gguf	Q4_1	4.87 GB	false	Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon.
Qwen2.5-7B-Instruct-1M-Q4_K_M.gguf	Q4_K_M	4.68 GB	false	Good quality, default size for most use cases, recommended.
Qwen2.5-7B-Instruct-1M-Q4_K_S.gguf	Q4_K_S	4.46 GB	false	Slightly lower quality with more space savings, recommended.
Qwen2.5-7B-Instruct-1M-Q4_0.gguf	Q4_0	4.43 GB	false	Legacy format, offers online repacking for ARM and AVX CPU inference.
Qwen2.5-7B-Instruct-1M-Q3_K_L.gguf	Q3_K_L	4.09 GB	false	Lower quality but usable, good for low RAM availability.
Qwen2.5-7B-Instruct-1M-Q3_K_M.gguf	Q3_K_M	3.81 GB	false	Low quality.
Qwen2.5-7B-Instruct-1M-Q3_K_S.gguf	Q3_K_S	3.49 GB	false	Low quality, not recommended.
Qwen2.5-7B-Instruct-1M-Q2_K.gguf	Q2_K	3.02 GB	false	Very low quality but surprisingly usable.

Technical Details

Supports a context length of up to 1M tokens.

Significantly improved performance in handling long-context tasks while maintaining its capability in short tasks.

Accuracy degradation may occur for sequences exceeding 262,144 tokens until improved support is added.

For more information, check their blog here.

Downloading using huggingface-cli

Click to view download instructions

First, make sure you have hugginface-cli installed:

pip install -U "huggingface_hub[cli]"

Then, you can target the specific file you want:

huggingface-cli download BabaK07/Qwen2.5-7b-Instruct-1M-Q4_K_M-gguf --include "Qwen2.5-7b-Instruct-1M-Q4_K_M.gguf" --local-dir ./

Special thanks

🙏 Special thanks to Georgi Gerganov and the whole team working on llama.cpp for making all of this possible.

Downloads last month: 324

GGUF

Model size

8B params

Architecture

qwen2

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

16-bit

32-bit

Model tree for BabaK07/Qwen2.5-7B-Instruct-1M-GGUF

Base model

Qwen/Qwen2.5-7B

Finetuned

Qwen/Qwen2.5-7B-Instruct-1M

Quantized

(69)

this model

Collection including BabaK07/Qwen2.5-7B-Instruct-1M-GGUF

Quantized Models

Collection

2 items • Updated Feb 12, 2025