Instructions to use nassimjp/MiniCPM5-2B-SFT-Pashto-Instruct-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 nassimjp/MiniCPM5-2B-SFT-Pashto-Instruct-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 nassimjp/MiniCPM5-2B-SFT-Pashto-Instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf nassimjp/MiniCPM5-2B-SFT-Pashto-Instruct-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 nassimjp/MiniCPM5-2B-SFT-Pashto-Instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf nassimjp/MiniCPM5-2B-SFT-Pashto-Instruct-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 nassimjp/MiniCPM5-2B-SFT-Pashto-Instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf nassimjp/MiniCPM5-2B-SFT-Pashto-Instruct-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 nassimjp/MiniCPM5-2B-SFT-Pashto-Instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf nassimjp/MiniCPM5-2B-SFT-Pashto-Instruct-GGUF:Q4_K_M

Use Docker

docker model run hf.co/nassimjp/MiniCPM5-2B-SFT-Pashto-Instruct-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use nassimjp/MiniCPM5-2B-SFT-Pashto-Instruct-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "nassimjp/MiniCPM5-2B-SFT-Pashto-Instruct-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": "nassimjp/MiniCPM5-2B-SFT-Pashto-Instruct-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/nassimjp/MiniCPM5-2B-SFT-Pashto-Instruct-GGUF:Q4_K_M

Ollama
How to use nassimjp/MiniCPM5-2B-SFT-Pashto-Instruct-GGUF with Ollama:
```
ollama run hf.co/nassimjp/MiniCPM5-2B-SFT-Pashto-Instruct-GGUF:Q4_K_M
```
Unsloth Desktop

How to use nassimjp/MiniCPM5-2B-SFT-Pashto-Instruct-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf nassimjp/MiniCPM5-2B-SFT-Pashto-Instruct-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": "nassimjp/MiniCPM5-2B-SFT-Pashto-Instruct-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use nassimjp/MiniCPM5-2B-SFT-Pashto-Instruct-GGUF with Docker Model Runner:
```
docker model run hf.co/nassimjp/MiniCPM5-2B-SFT-Pashto-Instruct-GGUF:Q4_K_M
```

Lemonade

How to use nassimjp/MiniCPM5-2B-SFT-Pashto-Instruct-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull nassimjp/MiniCPM5-2B-SFT-Pashto-Instruct-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.MiniCPM5-2B-SFT-Pashto-Instruct-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use nassimjp/MiniCPM5-2B-SFT-Pashto-Instruct-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 nassimjp/MiniCPM5-2B-SFT-Pashto-Instruct-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 nassimjp/MiniCPM5-2B-SFT-Pashto-Instruct-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use nassimjp/MiniCPM5-2B-SFT-Pashto-Instruct-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf nassimjp/MiniCPM5-2B-SFT-Pashto-Instruct-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 "nassimjp/MiniCPM5-2B-SFT-Pashto-Instruct-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"

MiniCPM5-2B-SFT-Pashto-Instruct-GGUF 🚀⚡️🇦🇫

MiniCPM5-2B-SFT-Pashto-Instruct-GGUF contains optimized GGUF builds of nassimjp/MiniCPM5-2B-SFT-Pashto-Instruct. Designed for ultra-low latency, lightweight local execution, and seamless edge integration on CPUs, laptops, mobile devices, and consumer GPUs using llama.cpp and Ollama.

Highlights & Features

High Precision Execution: Includes full-precision f16 GGUF exports for maximum fidelity and zero degradation in Pashto token generation.
Edge Optimized: Run specialized Pashto LLMs locally on consumer hardware without high VRAM requirements.
Full Toolchain Compatibility: Ready for immediate deployment in llama.cpp, Ollama, LM Studio, and mobile runtime environments.

Quickstart & Usage Guide

1. Running with llama.cpp

Run directly from your command line using llama-cli:

# Clone or download the GGUF file
huggingface-cli download nassimjp/MiniCPM5-2B-SFT-Pashto-Instruct-GGUF MiniCPM5-2B-SFT-Pashto.F16.gguf --local-dir .

# Execute prompt
./llama-cli -m MiniCPM5-2B-SFT-Pashto.F16.gguf \
  -p "د پښتو او مصنوعي ځیرکتیا پرمختګ څرنګه ارزوې؟" \
  -n 256 \
  --temp 0.7

2. Running with Ollama

Create a simple Modelfile:

FROM ./MiniCPM5-2B-SFT-Pashto.F16.gguf
PARAMETER temperature 0.7
PARAMETER top_p 0.9
SYSTEM "تاسو یو هوښیار او مرسته کوونکی د پښتو ژبې د مصنوعي ځیرکتیا مرستیال یاست."

Create and launch the model:

ollama create pashto-minicpm -f Modelfile
ollama run pashto-minicpm "د افغان معارف په وده کې د ټیکنالوژۍ اغېزې څه دي؟"

Model Specifications

Property	Value
Base Architecture	MiniCPM-2B
Format	GGUF (`f16`)
Target Language	Pashto (`ps`)
Context Length	2048 Tokens
Framework Support	`llama.cpp`, `Ollama`, `vLLM`

Project Context

Developed under the iPashto.ai initiative, advancing open-weights Pashto Natural Language Processing (NLP) tools, quantization protocols, and edge deployment pipelines.

Downloads last month: -

GGUF

Model size

3B params

Architecture

llama

Hardware compatibility

4-bit

8-bit

16-bit

Model tree for nassimjp/MiniCPM5-2B-SFT-Pashto-Instruct-GGUF

Base model

openbmb/MiniCPM-2B-sft-bf16

Adapter

nassimjp/MiniCPM5-2B-SFT-Pashto-Instruct

Quantized

(1)

this model