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

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use PocketWeights/PocketWeights-Qwen2.5-7B-Instruct 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 PocketWeights/PocketWeights-Qwen2.5-7B-Instruct:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf PocketWeights/PocketWeights-Qwen2.5-7B-Instruct:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf PocketWeights/PocketWeights-Qwen2.5-7B-Instruct:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf PocketWeights/PocketWeights-Qwen2.5-7B-Instruct: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 PocketWeights/PocketWeights-Qwen2.5-7B-Instruct:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf PocketWeights/PocketWeights-Qwen2.5-7B-Instruct: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 PocketWeights/PocketWeights-Qwen2.5-7B-Instruct:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf PocketWeights/PocketWeights-Qwen2.5-7B-Instruct:Q4_K_M

Use Docker

docker model run hf.co/PocketWeights/PocketWeights-Qwen2.5-7B-Instruct:Q4_K_M

LM Studio
Jan
Ollama
How to use PocketWeights/PocketWeights-Qwen2.5-7B-Instruct with Ollama:
```
ollama run hf.co/PocketWeights/PocketWeights-Qwen2.5-7B-Instruct:Q4_K_M
```
Unsloth Desktop

How to use PocketWeights/PocketWeights-Qwen2.5-7B-Instruct with Pi:

Start the llama.cpp server

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

Run Pi

# Start Pi in your project directory:
pi

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

Lemonade

How to use PocketWeights/PocketWeights-Qwen2.5-7B-Instruct with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull PocketWeights/PocketWeights-Qwen2.5-7B-Instruct:Q4_K_M

Run and chat with the model

lemonade run user.PocketWeights-Qwen2.5-7B-Instruct-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use PocketWeights/PocketWeights-Qwen2.5-7B-Instruct with Hermes Agent:

Start the llama.cpp server

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

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use PocketWeights/PocketWeights-Qwen2.5-7B-Instruct with OpenClaw:

Start the llama.cpp server

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

⚡ PocketWeights: Qwen2.5-7B-Instruct (GGUF)

Heavy models, made light. PocketWeights specializes in targeted weight synthesis and hardware-friendly deployments for local AI practitioners.

Synthesized via out-of-core DARE-TIES weight merging and quantized through llama.cpp.

🧠 Model Pedigree

Primary Base: Qwen/Qwen2.5-7B-Instruct
Secondary Alignment: Qwen/Qwen2.5-Coder-7B-Instruct
Synthesis Engine: MergeKit (DARE-TIES)

📊 Hardware & VRAM Compatibility Guide

File	Format	Target VRAM	Best For Hardware
`Qwen2.5-7B-Instruct-Q4_K_M.gguf`	4-bit Medium	~5.5 – 6.5 GB	Consumer GPUs (RTX 3060/4060), 8GB Macs, CPU offload
`Qwen2.5-7B-Instruct-Q6_K.gguf`	6-bit	~7.5 – 8.5 GB	Near-lossless instruction precision, 10GB+ GPUs
`Qwen2.5-7B-Instruct-Q8_0.gguf`	8-bit	~9.0 – 10.5 GB	Highest numerical precision, 12GB GPUs, system RAM inference

🚀 Quickstart (Ollama)

Run directly from Hugging Face without manual downloads:

# 4-bit
ollama run hf.co/PocketWeights/PocketWeights-Qwen2.5-7B-Instruct:Qwen2.5-7B-Instruct-Q4_K_M

# 6-bit
ollama run hf.co/PocketWeights/PocketWeights-Qwen2.5-7B-Instruct:Qwen2.5-7B-Instruct-Q6_K

# 8-bit
ollama run hf.co/PocketWeights/PocketWeights-Qwen2.5-7B-Instruct:Qwen2.5-7B-Instruct-Q8_0

🤝 Support the PocketWeights Mission

I build, verify, and publish custom weight merges and quantization pipelines to provide high-quality, unrestricted, and hardware-friendly models to the open-source community for free.

Running conversion setups, cloud instances, and storage requires ongoing compute resources. If these models enhance your local workflow, save you API costs, or power your projects, consider supporting ongoing pipelines:

☕ Donation Options

Ko-fi: ko-fi.com/iamvishalnarayan
Web3 / Crypto (Polygon / ETH): 0x4FC189bf839A89259dd28DE8cD97883c49e15615

Tip: Transferring over the Polygon network keeps transaction gas fees below $0.01!

Downloads last month: 70

GGUF

Model size

8B params

Architecture

qwen2

Hardware compatibility

4-bit

6-bit

8-bit

Inference Providers NEW

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

Model tree for PocketWeights/PocketWeights-Qwen2.5-7B-Instruct

Qwen/Qwen2.5-7B-Instruct

Qwen/Qwen2.5-Coder-7B-Instruct

Merge model

this model