Instructions to use dsfsfdff/Swift-1.5-Qwen3.8-Flash-Next-GSQ-RCO-abliterated-IQ3_S-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use dsfsfdff/Swift-1.5-Qwen3.8-Flash-Next-GSQ-RCO-abliterated-IQ3_S-GGUF 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 dsfsfdff/Swift-1.5-Qwen3.8-Flash-Next-GSQ-RCO-abliterated-IQ3_S-GGUF:IQ3_S # Run inference directly in the terminal: llama cli -hf dsfsfdff/Swift-1.5-Qwen3.8-Flash-Next-GSQ-RCO-abliterated-IQ3_S-GGUF:IQ3_S
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf dsfsfdff/Swift-1.5-Qwen3.8-Flash-Next-GSQ-RCO-abliterated-IQ3_S-GGUF:IQ3_S # Run inference directly in the terminal: llama cli -hf dsfsfdff/Swift-1.5-Qwen3.8-Flash-Next-GSQ-RCO-abliterated-IQ3_S-GGUF:IQ3_S
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 dsfsfdff/Swift-1.5-Qwen3.8-Flash-Next-GSQ-RCO-abliterated-IQ3_S-GGUF:IQ3_S # Run inference directly in the terminal: ./build/bin/llama cli -hf dsfsfdff/Swift-1.5-Qwen3.8-Flash-Next-GSQ-RCO-abliterated-IQ3_S-GGUF:IQ3_S
Use Docker
docker model run hf.co/dsfsfdff/Swift-1.5-Qwen3.8-Flash-Next-GSQ-RCO-abliterated-IQ3_S-GGUF:IQ3_S
- Llama new
- LM Studio
- Jan
- vLLM
How to use dsfsfdff/Swift-1.5-Qwen3.8-Flash-Next-GSQ-RCO-abliterated-IQ3_S-GGUF with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "dsfsfdff/Swift-1.5-Qwen3.8-Flash-Next-GSQ-RCO-abliterated-IQ3_S-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": "dsfsfdff/Swift-1.5-Qwen3.8-Flash-Next-GSQ-RCO-abliterated-IQ3_S-GGUF", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/dsfsfdff/Swift-1.5-Qwen3.8-Flash-Next-GSQ-RCO-abliterated-IQ3_S-GGUF:IQ3_S
- Ollama
How to use dsfsfdff/Swift-1.5-Qwen3.8-Flash-Next-GSQ-RCO-abliterated-IQ3_S-GGUF with Ollama:
ollama run hf.co/dsfsfdff/Swift-1.5-Qwen3.8-Flash-Next-GSQ-RCO-abliterated-IQ3_S-GGUF:IQ3_S
- Unsloth Desktop
- Pi
How to use dsfsfdff/Swift-1.5-Qwen3.8-Flash-Next-GSQ-RCO-abliterated-IQ3_S-GGUF with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf dsfsfdff/Swift-1.5-Qwen3.8-Flash-Next-GSQ-RCO-abliterated-IQ3_S-GGUF:IQ3_S
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:9931/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "dsfsfdff/Swift-1.5-Qwen3.8-Flash-Next-GSQ-RCO-abliterated-IQ3_S-GGUF:IQ3_S" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use dsfsfdff/Swift-1.5-Qwen3.8-Flash-Next-GSQ-RCO-abliterated-IQ3_S-GGUF with Docker Model Runner:
docker model run hf.co/dsfsfdff/Swift-1.5-Qwen3.8-Flash-Next-GSQ-RCO-abliterated-IQ3_S-GGUF:IQ3_S
- Lemonade
How to use dsfsfdff/Swift-1.5-Qwen3.8-Flash-Next-GSQ-RCO-abliterated-IQ3_S-GGUF with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull dsfsfdff/Swift-1.5-Qwen3.8-Flash-Next-GSQ-RCO-abliterated-IQ3_S-GGUF:IQ3_S
Run and chat with the model
lemonade run user.Swift-1.5-Qwen3.8-Flash-Next-GSQ-RCO-abliterated-IQ3_S-GGUF-IQ3_S
List all available models
lemonade list
- Hermes Agent
How to use dsfsfdff/Swift-1.5-Qwen3.8-Flash-Next-GSQ-RCO-abliterated-IQ3_S-GGUF with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf dsfsfdff/Swift-1.5-Qwen3.8-Flash-Next-GSQ-RCO-abliterated-IQ3_S-GGUF:IQ3_S
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://127.0.0.1:9931/v1 hermes config set model.default dsfsfdff/Swift-1.5-Qwen3.8-Flash-Next-GSQ-RCO-abliterated-IQ3_S-GGUF:IQ3_S
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use dsfsfdff/Swift-1.5-Qwen3.8-Flash-Next-GSQ-RCO-abliterated-IQ3_S-GGUF with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf dsfsfdff/Swift-1.5-Qwen3.8-Flash-Next-GSQ-RCO-abliterated-IQ3_S-GGUF:IQ3_S
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://127.0.0.1:9931/v1 \ --custom-model-id "dsfsfdff/Swift-1.5-Qwen3.8-Flash-Next-GSQ-RCO-abliterated-IQ3_S-GGUF:IQ3_S" \ --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"
Swift 1.5 Qwen3.8-Flash-Next GSQ-RCO abliterated โ IQ3_S (3-Shard Distribution)
Re-sharded version of SC117/Swift-1.5-Qwen3.8-Flash-Next-GSQ-RCO-abliterated-GGUF split into 3 shards specifically designed for constrained-storage environments (such as Kaggle / Colab with limited working partitions):
| Shard File | Size | Tensors |
|---|---|---|
Swift-Qwen3.8-Flash-Next-GSQ-RCO-abliterated-IQ3_S-00001-of-00003.gguf |
44.85 GB | 373 |
Swift-Qwen3.8-Flash-Next-GSQ-RCO-abliterated-IQ3_S-00002-of-00003.gguf |
13.71 GB | 329 |
Swift-Qwen3.8-Flash-Next-GSQ-RCO-abliterated-IQ3_S-00003-of-00003.gguf |
23.98 GB | 522 |
| Total | 83.54 GB | 1,224 |
Highlights
- 100% bit-exact: Identical quantization weights as SC117 / UkisAI Swift 1.5 GSQ-RCO.
- Kaggle / Constrained-disk Ready: Shard 2 is under 15 GB to easily fit in
/kaggle/workingwhile Shards 1 & 3 fit within/tmp(< 70 GB). - Native support in Strata and llama.cpp.
- Downloads last month
- 451
3-bit
Model tree for dsfsfdff/Swift-1.5-Qwen3.8-Flash-Next-GSQ-RCO-abliterated-IQ3_S-GGUF
Base model
Qwen/Qwen3.8-Flash-Next