Instructions to use redponike/Ring-mini-2.0-GGUF-ik with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use redponike/Ring-mini-2.0-GGUF-ik with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="redponike/Ring-mini-2.0-GGUF-ik")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("redponike/Ring-mini-2.0-GGUF-ik", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use redponike/Ring-mini-2.0-GGUF-ik 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 redponike/Ring-mini-2.0-GGUF-ik:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf redponike/Ring-mini-2.0-GGUF-ik:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf redponike/Ring-mini-2.0-GGUF-ik:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf redponike/Ring-mini-2.0-GGUF-ik: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 redponike/Ring-mini-2.0-GGUF-ik:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf redponike/Ring-mini-2.0-GGUF-ik: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 redponike/Ring-mini-2.0-GGUF-ik:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf redponike/Ring-mini-2.0-GGUF-ik:Q4_K_M

Use Docker

docker model run hf.co/redponike/Ring-mini-2.0-GGUF-ik:Q4_K_M

LM Studio
Jan

vLLM

How to use redponike/Ring-mini-2.0-GGUF-ik with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "redponike/Ring-mini-2.0-GGUF-ik"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "redponike/Ring-mini-2.0-GGUF-ik",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/redponike/Ring-mini-2.0-GGUF-ik:Q4_K_M

SGLang

How to use redponike/Ring-mini-2.0-GGUF-ik with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "redponike/Ring-mini-2.0-GGUF-ik" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "redponike/Ring-mini-2.0-GGUF-ik",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "redponike/Ring-mini-2.0-GGUF-ik" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "redponike/Ring-mini-2.0-GGUF-ik",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use redponike/Ring-mini-2.0-GGUF-ik with Ollama:
```
ollama run hf.co/redponike/Ring-mini-2.0-GGUF-ik:Q4_K_M
```

Unsloth Studio

How to use redponike/Ring-mini-2.0-GGUF-ik 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 redponike/Ring-mini-2.0-GGUF-ik 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 redponike/Ring-mini-2.0-GGUF-ik to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for redponike/Ring-mini-2.0-GGUF-ik to start chatting

Docker Model Runner
How to use redponike/Ring-mini-2.0-GGUF-ik with Docker Model Runner:
```
docker model run hf.co/redponike/Ring-mini-2.0-GGUF-ik:Q4_K_M
```

Lemonade

How to use redponike/Ring-mini-2.0-GGUF-ik with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull redponike/Ring-mini-2.0-GGUF-ik:Q4_K_M

Run and chat with the model

lemonade run user.Ring-mini-2.0-GGUF-ik-Q4_K_M

List all available models

lemonade list

Atomic Chat

These are NOT compatible with llama.cpp and its frontends and derivatives (LMStudio, Kobold, etc...). Use with ik_llama.cpp only.

Make sure to pass the -ger option to llama-server or llama-cli to enable grouped experts.

GGUF quants of Ring-mini-2.0

Using ik_llama.cpp (commit dbfd151594d723b8bed54326cb521d1bccfad802)

The importance matrix was generated with eaddario/imatrix-calibration combined_all_medium dataset and grouped experts option enabled.

All quants were generated/calibrated with the imatrix, including the K quants.

Compressed from BF16.

Ring-mini-2.0

🤗 Hugging Face | 🤖 ModelScope | 🐙 Experience Now

Today, we officially release Ring-mini-2.0 — a high-performance inference-oriented MoE model deeply optimized based on the Ling 2.0 architecture. With only 16B total parameters and 1.4B activated parameters, it achieves comprehensive reasoning capabilities comparable to dense models below the 10B scale. It excels particularly in logical reasoning, code generation, and mathematical tasks, while supporting 128K long-context processing and 300+ tokens/s high-speed generation.

Enhanced Reasoning: Joint Training with SFT + RLVR + RLHF

Built upon Ling-mini-2.0-base, Ring-mini-2.0 undergoes further training with Long-CoT SFT, more stable and continuous RLVR, and RLHF joint optimization, significantly improving the stability and generalization of complex reasoning. On multiple challenging benchmarks (LiveCodeBench, AIME 2025, GPQA, ARC-AGI-v1, etc.), it outperforms dense models below 10B and even rivals larger MoE models (e.g., gpt-oss-20B-medium) with comparable output lengths, particularly excelling in logical reasoning.

High Sparsity, High-Speed Generation

Inheriting the efficient MoE design of the Ling 2.0 series, Ring-mini-2.0 activates only 1.4B parameters and achieves performance equivalent to 7–8B dense models through architectural optimizations such as 1/32 expert activation ratio and MTP layers. Thanks to its low activation and high sparsity design, Ring-mini-2.0 delivers a throughput of 300+ tokens/s when deployed on H20. With Expert Dual Streaming inference optimization, this can be further boosted to 500+ tokens/s, significantly reducing inference costs for high-concurrency scenarios involving thinking models. Additionally, with YaRN extrapolation, it supports 128K long-context processing, achieving a relative speedup of up to 7x in long-output scenarios.