Instructions to use Slavish123/suvidya-600m with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use Slavish123/suvidya-600m 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 Slavish123/suvidya-600m:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Slavish123/suvidya-600m:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Slavish123/suvidya-600m:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Slavish123/suvidya-600m:Q4_K_M

Build from source code

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 Slavish123/suvidya-600m:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama cli -hf Slavish123/suvidya-600m:Q4_K_M

Use Docker

docker model run hf.co/Slavish123/suvidya-600m:Q4_K_M

Llama new
LM Studio
Jan
Ollama
How to use Slavish123/suvidya-600m with Ollama:
```
ollama run hf.co/Slavish123/suvidya-600m:Q4_K_M
```
Unsloth Desktop

How to use Slavish123/suvidya-600m with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Slavish123/suvidya-600m: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": "Slavish123/suvidya-600m:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use Slavish123/suvidya-600m with Docker Model Runner:
```
docker model run hf.co/Slavish123/suvidya-600m:Q4_K_M
```

Lemonade

How to use Slavish123/suvidya-600m with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Slavish123/suvidya-600m:Q4_K_M

Run and chat with the model

lemonade run user.suvidya-600m-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use Slavish123/suvidya-600m with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Slavish123/suvidya-600m: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 Slavish123/suvidya-600m:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Slavish123/suvidya-600m with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Slavish123/suvidya-600m: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 "Slavish123/suvidya-600m: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"

Suvidya-600M

Suvidya-600M is a highly specialized 600M parameter math reasoning model. It solves complex competition math and grade-school math by generating and executing Python code (TIR - Tool-Integrated Reasoning).

Benchmarks

Benchmark	Score	Note
GSM8K	62.4%	Pass@1, TIR
MATH-500	34.0%	Pass@1, TIR
HumanEval	24.39%	Pass@1 (Python)
ARC-Challenge	42.41%	25-shot (Beats base Qwen3-0.6B)

How to run locally with Ollama

Download the Modelfile from this repo: curl -O https://huggingface.co/Slavish123/suvidya-600m/resolve/main/Modelfile
Build the model: ollama create suvidya-600m -f Modelfile
Run it: ollama run suvidya-600m

Part of the Suvidya ecosystem.

Downloads last month: 62

GGUF

Model size

0.6B params

Architecture

qwen3

Hardware compatibility

4-bit

16-bit

Inference Providers NEW

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

Model tree for Slavish123/suvidya-600m

Base model

Qwen/Qwen3-0.6B-Base

Finetuned

Qwen/Qwen3-0.6B

Quantized

(522)

this model

Slavish123
/

suvidya-600m

Suvidya-600M

Benchmarks

How to run locally with Ollama

Model tree for Slavish123/suvidya-600m

Dataset used to train Slavish123/suvidya-600m