π¦ GGUF Quants
Collection
111 items β’ Updated β’ 1
How to use tinyopsec/MiniCPM5-2B-SFT-Pashto-GGUF with llama.cpp:
curl -LsSf https://llama.app/install.sh | sh # Start a local OpenAI-compatible server with a web UI: llama serve -hf tinyopsec/MiniCPM5-2B-SFT-Pashto-GGUF:Q4_K_M # Run inference directly in the terminal: llama cli -hf tinyopsec/MiniCPM5-2B-SFT-Pashto-GGUF:Q4_K_M
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf tinyopsec/MiniCPM5-2B-SFT-Pashto-GGUF:Q4_K_M # Run inference directly in the terminal: llama cli -hf tinyopsec/MiniCPM5-2B-SFT-Pashto-GGUF:Q4_K_M
git clone https://github.com/ggml-org/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-app # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama serve -hf tinyopsec/MiniCPM5-2B-SFT-Pashto-GGUF:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama cli -hf tinyopsec/MiniCPM5-2B-SFT-Pashto-GGUF:Q4_K_M
docker model run hf.co/tinyopsec/MiniCPM5-2B-SFT-Pashto-GGUF:Q4_K_M
How to use tinyopsec/MiniCPM5-2B-SFT-Pashto-GGUF with vLLM:
# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tinyopsec/MiniCPM5-2B-SFT-Pashto-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": "tinyopsec/MiniCPM5-2B-SFT-Pashto-GGUF",
"messages": [
{
"role": "user",
"content": "What is the capital of France?"
}
]
}'docker model run hf.co/tinyopsec/MiniCPM5-2B-SFT-Pashto-GGUF:Q4_K_M
How to use tinyopsec/MiniCPM5-2B-SFT-Pashto-GGUF with Ollama:
ollama run hf.co/tinyopsec/MiniCPM5-2B-SFT-Pashto-GGUF:Q4_K_M
How to use tinyopsec/MiniCPM5-2B-SFT-Pashto-GGUF with Pi:
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf tinyopsec/MiniCPM5-2B-SFT-Pashto-GGUF:Q4_K_M
# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
"providers": {
"llama-cpp": {
"baseUrl": "http://localhost:9931/v1",
"api": "openai-completions",
"apiKey": "none",
"models": [
{
"id": "tinyopsec/MiniCPM5-2B-SFT-Pashto-GGUF:Q4_K_M"
}
]
}
}
}# Start Pi in your project directory: pi
How to use tinyopsec/MiniCPM5-2B-SFT-Pashto-GGUF with Docker Model Runner:
docker model run hf.co/tinyopsec/MiniCPM5-2B-SFT-Pashto-GGUF:Q4_K_M
How to use tinyopsec/MiniCPM5-2B-SFT-Pashto-GGUF with Lemonade:
# Download Lemonade from https://lemonade-server.ai/ lemonade pull tinyopsec/MiniCPM5-2B-SFT-Pashto-GGUF:Q4_K_M
lemonade run user.MiniCPM5-2B-SFT-Pashto-GGUF-Q4_K_M
lemonade list
How to use tinyopsec/MiniCPM5-2B-SFT-Pashto-GGUF with Hermes Agent:
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf tinyopsec/MiniCPM5-2B-SFT-Pashto-GGUF:Q4_K_M
# 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://127.0.0.1:9931/v1 hermes config set model.default tinyopsec/MiniCPM5-2B-SFT-Pashto-GGUF:Q4_K_M
hermes
How to use tinyopsec/MiniCPM5-2B-SFT-Pashto-GGUF with OpenClaw:
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf tinyopsec/MiniCPM5-2B-SFT-Pashto-GGUF:Q4_K_M
# 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://127.0.0.1:9931/v1 \ --custom-model-id "tinyopsec/MiniCPM5-2B-SFT-Pashto-GGUF:Q4_K_M" \ --custom-provider-id llama-cpp \ --custom-compatibility openai \ --custom-text-input \ --accept-risk \ --skip-health
openclaw agent --local --agent main --message "Hello from Hugging Face"
GGUF quantizations of nassimjp/MiniCPM5-2B-SFT-Pashto, a fine-tuned version of openbmb/MiniCPM5-2B for Pashto language.
| File | Bits | Est. Size | Use Case |
|---|---|---|---|
| model_f16.gguf | 16 | ~4.6 GB | Reference / re-quantization |
| model_q8_0.gguf | 8 | ~2.4 GB | Max quality, enough RAM |
| model_q6_k.gguf | 6 | ~1.9 GB | High quality |
| model_q5_k_m.gguf | 5 | ~1.6 GB | Balanced |
| model_q5_k_s.gguf | 5 | ~1.6 GB | Balanced, smaller |
| model_q4_k_m.gguf | 4 | ~1.4 GB | Recommended |
| model_q4_k_s.gguf | 4 | ~1.3 GB | Lower RAM |
| model_q3_k_l.gguf | 3 | ~1.1 GB | Low RAM |
| model_q3_k_m.gguf | 3 | ~1.0 GB | Low RAM |
| model_q3_k_s.gguf | 3 | ~0.9 GB | Minimum quality |
| model_q2_k.gguf | 2 | ~0.7 GB | Very low RAM only |
| Quant | RAM |
|---|---|
| Q8_0 | ~3 GB |
| Q4_K_M | ~2 GB |
| Q2_K | ~1.5 GB |
./llama-cli -m model_q4_k_m.gguf -p "Your prompt here" -n 256
from llama_cpp import Llama
llm = Llama(model_path="model_q4_k_m.gguf")
output = llm("Your prompt here", max_tokens=256)
print(output["choices"][0]["text"])
Download any .gguf file and load directly in LM Studio.
ollama run hf.co/tinyopsec/MiniCPM5-2B-SFT-Pashto-GGUF:Q4_K_M
LlamaForCausalLM--min-p 0.0 to avoid repetition2-bit
3-bit
4-bit
5-bit
6-bit
8-bit
16-bit