Instructions to use vahpetr/MiniCPM5-1B-ru-v3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use vahpetr/MiniCPM5-1B-ru-v3 with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="vahpetr/MiniCPM5-1B-ru-v3",
	filename="MiniCPM5-1B-ru-v3-Q8_0.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use vahpetr/MiniCPM5-1B-ru-v3 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 vahpetr/MiniCPM5-1B-ru-v3:Q8_0
# Run inference directly in the terminal:
llama cli -hf vahpetr/MiniCPM5-1B-ru-v3:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf vahpetr/MiniCPM5-1B-ru-v3:Q8_0
# Run inference directly in the terminal:
llama cli -hf vahpetr/MiniCPM5-1B-ru-v3:Q8_0

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 vahpetr/MiniCPM5-1B-ru-v3:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf vahpetr/MiniCPM5-1B-ru-v3:Q8_0

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 vahpetr/MiniCPM5-1B-ru-v3:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf vahpetr/MiniCPM5-1B-ru-v3:Q8_0

Use Docker

docker model run hf.co/vahpetr/MiniCPM5-1B-ru-v3:Q8_0

LM Studio
Jan
Ollama
How to use vahpetr/MiniCPM5-1B-ru-v3 with Ollama:
```
ollama run hf.co/vahpetr/MiniCPM5-1B-ru-v3:Q8_0
```

Unsloth Studio

How to use vahpetr/MiniCPM5-1B-ru-v3 with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for vahpetr/MiniCPM5-1B-ru-v3 to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for vahpetr/MiniCPM5-1B-ru-v3 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for vahpetr/MiniCPM5-1B-ru-v3 to start chatting

How to use vahpetr/MiniCPM5-1B-ru-v3 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf vahpetr/MiniCPM5-1B-ru-v3:Q8_0

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "vahpetr/MiniCPM5-1B-ru-v3:Q8_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use vahpetr/MiniCPM5-1B-ru-v3 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf vahpetr/MiniCPM5-1B-ru-v3:Q8_0

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 vahpetr/MiniCPM5-1B-ru-v3:Q8_0

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use vahpetr/MiniCPM5-1B-ru-v3 with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf vahpetr/MiniCPM5-1B-ru-v3:Q8_0

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 "vahpetr/MiniCPM5-1B-ru-v3:Q8_0" \
  --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"

Docker Model Runner
How to use vahpetr/MiniCPM5-1B-ru-v3 with Docker Model Runner:
```
docker model run hf.co/vahpetr/MiniCPM5-1B-ru-v3:Q8_0
```

Lemonade

How to use vahpetr/MiniCPM5-1B-ru-v3 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull vahpetr/MiniCPM5-1B-ru-v3:Q8_0

Run and chat with the model

lemonade run user.MiniCPM5-1B-ru-v3-Q8_0

List all available models

lemonade list

MiniCPM5-1B-ru (v3, merged, experimental)

openbmb/MiniCPM5-1B with a Russian LoRA (v3) merged in, to improve practical Russian (customer-support style, everyday instructions, translation) while keeping the base's coding ability. Trained on Vikhrmodels/GrandMaster-PRO-MAX (Russian + English, chain-of-thought) plus an English replay slice, on an AMD Strix Halo iGPU (ROCm). Adapter-only version: vahpetr/MiniCPM5-1B-ru-lora-v3.

Honest evaluation (base vs this, thinking OFF, 3-run avg on local batteries)

axis	base	this	note
Reasoning (/18)	~16	~12	↓ tradeoff
IFEval (/10)	~8	~5	↓ tradeoff
Code (/7)	7	7	preserved
Agentic tool-use (/10)	~6	~5	≈ preserved
General / Ortho (/23)	~12	~13	↑ (customer-service, translation)
Russian math battery	low	low	unchanged (1B math-capped)

What it does well: practical Russian gets noticeably more fluent and coherent (customer-support replies become natural Russian instead of English/Chinese-mixed; RU→EN translation more accurate).

The tradeoff: sharp reasoning and strict instruction-following drop somewhat — an inherent 1B capacity limit. For strong Russian without the tradeoff, use a Russian-native model or a larger base.

Use thinking OFF (enable_thinking=false).

Usage

Load as a normal model (transformers / vLLM). A Q8_0 GGUF (MiniCPM5-1B-ru-v3-Q8_0.gguf) is included for Ollama / LM Studio / llama.cpp.

from transformers import AutoModelForCausalLM, AutoTokenizer
m = AutoModelForCausalLM.from_pretrained("vahpetr/MiniCPM5-1B-ru-v3", trust_remote_code=True)
tok = AutoTokenizer.from_pretrained("vahpetr/MiniCPM5-1B-ru-v3", trust_remote_code=True)

Attribution & license

Base: MiniCPM5-1B (OpenBMB) — Apache-2.0
Data: GrandMaster-PRO-MAX (Vikhr) — Apache-2.0
This model — Apache-2.0

Downloads last month: 185

Safetensors

Model size

1B params

Tensor type

BF16

Inference Providers NEW

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

Model tree for vahpetr/MiniCPM5-1B-ru-v3

Base model

openbmb/MiniCPM5-1B

Quantized

(78)

this model