Instructions to use ssweens/Ling-2.6-flash-GGUF-YMMV with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ssweens/Ling-2.6-flash-GGUF-YMMV with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="ssweens/Ling-2.6-flash-GGUF-YMMV",
	filename="inclusionAI__Ling-2.6-flash-IQ2_XS.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use ssweens/Ling-2.6-flash-GGUF-YMMV with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf ssweens/Ling-2.6-flash-GGUF-YMMV:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf ssweens/Ling-2.6-flash-GGUF-YMMV:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf ssweens/Ling-2.6-flash-GGUF-YMMV:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf ssweens/Ling-2.6-flash-GGUF-YMMV: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 ssweens/Ling-2.6-flash-GGUF-YMMV:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf ssweens/Ling-2.6-flash-GGUF-YMMV: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 ssweens/Ling-2.6-flash-GGUF-YMMV:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf ssweens/Ling-2.6-flash-GGUF-YMMV:Q4_K_M

Use Docker

docker model run hf.co/ssweens/Ling-2.6-flash-GGUF-YMMV:Q4_K_M

LM Studio
Jan

vLLM

How to use ssweens/Ling-2.6-flash-GGUF-YMMV with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ssweens/Ling-2.6-flash-GGUF-YMMV"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ssweens/Ling-2.6-flash-GGUF-YMMV",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ssweens/Ling-2.6-flash-GGUF-YMMV:Q4_K_M

Ollama
How to use ssweens/Ling-2.6-flash-GGUF-YMMV with Ollama:
```
ollama run hf.co/ssweens/Ling-2.6-flash-GGUF-YMMV:Q4_K_M
```

Unsloth Studio

How to use ssweens/Ling-2.6-flash-GGUF-YMMV 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 ssweens/Ling-2.6-flash-GGUF-YMMV 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 ssweens/Ling-2.6-flash-GGUF-YMMV to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for ssweens/Ling-2.6-flash-GGUF-YMMV to start chatting

How to use ssweens/Ling-2.6-flash-GGUF-YMMV with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf ssweens/Ling-2.6-flash-GGUF-YMMV:Q4_K_M

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": "ssweens/Ling-2.6-flash-GGUF-YMMV:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use ssweens/Ling-2.6-flash-GGUF-YMMV with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf ssweens/Ling-2.6-flash-GGUF-YMMV: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 ssweens/Ling-2.6-flash-GGUF-YMMV:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use ssweens/Ling-2.6-flash-GGUF-YMMV with Docker Model Runner:
```
docker model run hf.co/ssweens/Ling-2.6-flash-GGUF-YMMV:Q4_K_M
```

Lemonade

How to use ssweens/Ling-2.6-flash-GGUF-YMMV with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ssweens/Ling-2.6-flash-GGUF-YMMV:Q4_K_M

Run and chat with the model

lemonade run user.Ling-2.6-flash-GGUF-YMMV-Q4_K_M

List all available models

lemonade list

🧪 Experimental GGUFs for Ling-2.6-flash

A stopgap to experiment with Ling 2.6 locally while the tools ecosystem catches up. Expect rough edges. Validated for text and coding coherence.

GGUF files for inclusionAI/Ling-2.6-flash.

⚠️ You need the custom fork

These GGUFs require a Ling-2.6-capable fork of llama.cpp. Vanilla llama.cpp doesn't support the BailingMoeV2.5 architecture yet.

llama.cpp fork: ssweens/llama.cpp-ling-2.6
Backends: Tested on CUDA and ROCm.

Performance

Example:

llama-server -ngl 99 --no-mmap -fa on -np 1 --reasoning-format auto --jinja --threads 3 -ts 4,4,3 -dev CUDA0,CUDA1,CUDA2 
-m /mnt/supmodels/gguf/inclusionAI__Ling-2.6-flash/inclusionAI__Ling-2.6-flash-Q4_K_M.gguf -c 32768 -b 2048 -ub 512 -ctk q8_0 -ctv q8_0

Speed (custom, n=2)

Model	Prompt t/s	Gen t/s	TTFT s	Decode s	Backend
IQ2_XS	1438.08	34.58	0.64	3.70	CUDA
Q2_K	1407.68	34.30	0.65	3.73	CUDA
Q4_K_M	1176.48	27.09	0.78	4.72	CUDA
Q8_0	531.16	15.35	1.66	8.34	CUDA+ROCm

Coding (humaneval_instruct, n=30)

Model	pass@1	Backend
IQ2_XS	0.933±0.046	CUDA
Q2_K	0.967±0.033	CUDA
Q4_K_M	1.000±0.000	CUDA
Q8_0	1.000±0.000	CUDA+ROCm

Original model

inclusionAI/Ling-2.6-flash

Thanks

inclusionAI — open model weights, architecture, and the BailingMoeV2.5 design
llama.cpp — the project that makes local LLM inference possible

Downloads last month: 540

GGUF

Model size

108B params

Architecture

bailingmoe2.5

Hardware compatibility

2-bit

4-bit

8-bit

Model tree for ssweens/Ling-2.6-flash-GGUF-YMMV

Base model

inclusionAI/Ling-2.6-flash

Quantized

(9)

this model