Instructions to use yue-neg-613/Swift-1.5-Qwen3.8-27b-QSA 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 yue-neg-613/Swift-1.5-Qwen3.8-27b-QSA 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 yue-neg-613/Swift-1.5-Qwen3.8-27b-QSA:BF16 # Run inference directly in the terminal: llama cli -hf yue-neg-613/Swift-1.5-Qwen3.8-27b-QSA:BF16
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf yue-neg-613/Swift-1.5-Qwen3.8-27b-QSA:BF16 # Run inference directly in the terminal: llama cli -hf yue-neg-613/Swift-1.5-Qwen3.8-27b-QSA:BF16
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 yue-neg-613/Swift-1.5-Qwen3.8-27b-QSA:BF16 # Run inference directly in the terminal: ./build/bin/llama cli -hf yue-neg-613/Swift-1.5-Qwen3.8-27b-QSA:BF16
Use Docker
docker model run hf.co/yue-neg-613/Swift-1.5-Qwen3.8-27b-QSA:BF16
- Llama new
- LM Studio
- Jan
- Ollama
How to use yue-neg-613/Swift-1.5-Qwen3.8-27b-QSA with Ollama:
ollama run hf.co/yue-neg-613/Swift-1.5-Qwen3.8-27b-QSA:BF16
- Unsloth Desktop
- Pi
How to use yue-neg-613/Swift-1.5-Qwen3.8-27b-QSA with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf yue-neg-613/Swift-1.5-Qwen3.8-27b-QSA:BF16
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": "yue-neg-613/Swift-1.5-Qwen3.8-27b-QSA:BF16" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use yue-neg-613/Swift-1.5-Qwen3.8-27b-QSA with Docker Model Runner:
docker model run hf.co/yue-neg-613/Swift-1.5-Qwen3.8-27b-QSA:BF16
- Lemonade
How to use yue-neg-613/Swift-1.5-Qwen3.8-27b-QSA with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull yue-neg-613/Swift-1.5-Qwen3.8-27b-QSA:BF16
Run and chat with the model
lemonade run user.Swift-1.5-Qwen3.8-27b-QSA-BF16
List all available models
lemonade list
- Hermes Agent
How to use yue-neg-613/Swift-1.5-Qwen3.8-27b-QSA with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf yue-neg-613/Swift-1.5-Qwen3.8-27b-QSA:BF16
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 yue-neg-613/Swift-1.5-Qwen3.8-27b-QSA:BF16
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use yue-neg-613/Swift-1.5-Qwen3.8-27b-QSA with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf yue-neg-613/Swift-1.5-Qwen3.8-27b-QSA:BF16
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 "yue-neg-613/Swift-1.5-Qwen3.8-27b-QSA:BF16" \ --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-Qwen3.8-27B-QSA-bf16
Overview
This model employs the methodology described at https://huggingface.co/higa2515/Qwen3.8-27B-QSA-BF16, replacing the Global Attention layerโwhich traditionally consists of Grouped Query Attentionโwith QSA (Qwen Sparse Attention) as used in Qwen3.8-Flash-Next.
This model was created for the purpose of verifying QSA replacement technology. As it is not intended for inference in real-world environments, please be aware of this before use.
Limitations
We have not developed an Indexer for image-based mapping models. Additionally, please note that since no modifications have been made to MTP, Vision and MTP cannot be enabled.
The following product is required to run this model: https://github.com/kuraneko1/Qwen3.8-27B-QSA-llama.cpp Please install it as needed before trying it out.
Licensing
This model is treated as a derivative of Swift-1.5-Qwen3.8-27B and is therefore subject to the license terms defined therein. Specifically, it follows the [Swift Open License v1.0].
Accordingly, those intending to use this model for commercial purposes are requested to consult with ukisAI separately.
Qwen3.8-27B-QSA
Full multimodal backbone, with trained QSA indexers on text decoder full-attention layers. Text-only requests use QSA (K=2048, r=4). Image/video requests, including subsequent cached generation, use original dense attention. Padded requests also use dense attention. Backbone weights, vision encoder, MTP tensors, tokenizer, processor and chat template are preserved.
Load
Install the tested runtime with pip install -r requirements.txt.
The indexers remain FP32; backbone weights remain BF16.
from transformers import AutoModelForImageTextToText, AutoProcessor
path = '/absolute/path/to/Qwen3.8-27B-QSA'
processor = AutoProcessor.from_pretrained(path, trust_remote_code=True)
model = AutoModelForImageTextToText.from_pretrained(
path, trust_remote_code=True, dtype='auto', device_map='auto',
attn_implementation='sdpa',
)
# Use processor.apply_chat_template(...) and model.generate(...) as for the base model.
Status
This runtime uses a dense Boolean mask as a correctness reference, not an optimized sparse kernel.
No inference speedup is claimed. Use the default dynamic cache; speculative rollback, MTP
execution, static/quantized caches and continuous batching are not implemented here.
The original MTP weights are retained for future work. See conversion_manifest.json for provenance
and validation limits, and BASE_MODEL_CARD.md for the original model card.
- Downloads last month
- 1,040