Instructions to use ukisai/Swift-1.5-Qwen3.8-Flash-Next-GSQ-RCO-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use ukisai/Swift-1.5-Qwen3.8-Flash-Next-GSQ-RCO-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 ukisai/Swift-1.5-Qwen3.8-Flash-Next-GSQ-RCO-GGUF:IQ2_XS
# Run inference directly in the terminal:
llama cli -hf ukisai/Swift-1.5-Qwen3.8-Flash-Next-GSQ-RCO-GGUF:IQ2_XS

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf ukisai/Swift-1.5-Qwen3.8-Flash-Next-GSQ-RCO-GGUF:IQ2_XS
# Run inference directly in the terminal:
llama cli -hf ukisai/Swift-1.5-Qwen3.8-Flash-Next-GSQ-RCO-GGUF:IQ2_XS

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 ukisai/Swift-1.5-Qwen3.8-Flash-Next-GSQ-RCO-GGUF:IQ2_XS
# Run inference directly in the terminal:
./llama-cli -hf ukisai/Swift-1.5-Qwen3.8-Flash-Next-GSQ-RCO-GGUF:IQ2_XS

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 ukisai/Swift-1.5-Qwen3.8-Flash-Next-GSQ-RCO-GGUF:IQ2_XS
# Run inference directly in the terminal:
./build/bin/llama-cli -hf ukisai/Swift-1.5-Qwen3.8-Flash-Next-GSQ-RCO-GGUF:IQ2_XS

Use Docker

docker model run hf.co/ukisai/Swift-1.5-Qwen3.8-Flash-Next-GSQ-RCO-GGUF:IQ2_XS

LM Studio
Jan

vLLM

How to use ukisai/Swift-1.5-Qwen3.8-Flash-Next-GSQ-RCO-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ukisai/Swift-1.5-Qwen3.8-Flash-Next-GSQ-RCO-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": "ukisai/Swift-1.5-Qwen3.8-Flash-Next-GSQ-RCO-GGUF",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/ukisai/Swift-1.5-Qwen3.8-Flash-Next-GSQ-RCO-GGUF:IQ2_XS

Ollama
How to use ukisai/Swift-1.5-Qwen3.8-Flash-Next-GSQ-RCO-GGUF with Ollama:
```
ollama run hf.co/ukisai/Swift-1.5-Qwen3.8-Flash-Next-GSQ-RCO-GGUF:IQ2_XS
```
Unsloth Desktop

How to use ukisai/Swift-1.5-Qwen3.8-Flash-Next-GSQ-RCO-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ukisai/Swift-1.5-Qwen3.8-Flash-Next-GSQ-RCO-GGUF:IQ2_XS

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": "ukisai/Swift-1.5-Qwen3.8-Flash-Next-GSQ-RCO-GGUF:IQ2_XS"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use ukisai/Swift-1.5-Qwen3.8-Flash-Next-GSQ-RCO-GGUF with Docker Model Runner:
```
docker model run hf.co/ukisai/Swift-1.5-Qwen3.8-Flash-Next-GSQ-RCO-GGUF:IQ2_XS
```

Lemonade

How to use ukisai/Swift-1.5-Qwen3.8-Flash-Next-GSQ-RCO-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ukisai/Swift-1.5-Qwen3.8-Flash-Next-GSQ-RCO-GGUF:IQ2_XS

Run and chat with the model

lemonade run user.Swift-1.5-Qwen3.8-Flash-Next-GSQ-RCO-GGUF-IQ2_XS

List all available models

lemonade list

Hermes Agent

How to use ukisai/Swift-1.5-Qwen3.8-Flash-Next-GSQ-RCO-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 ukisai/Swift-1.5-Qwen3.8-Flash-Next-GSQ-RCO-GGUF:IQ2_XS

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 ukisai/Swift-1.5-Qwen3.8-Flash-Next-GSQ-RCO-GGUF:IQ2_XS

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use ukisai/Swift-1.5-Qwen3.8-Flash-Next-GSQ-RCO-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ukisai/Swift-1.5-Qwen3.8-Flash-Next-GSQ-RCO-GGUF:IQ2_XS

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 "ukisai/Swift-1.5-Qwen3.8-Flash-Next-GSQ-RCO-GGUF:IQ2_XS" \
  --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-GGUF / evaluation /heldout-kld.tsv

ukisai

initial release

b22d729 1 day ago

Raw

History Blame Contribute Delete

2.49 kB

	tier domain kld reported_error chunks context ista_kld starter_kld delta_vs_ista_pct delta_vs_starter_pct
	IQ2_XS prose_c4 0.188117 0.001955 100 512 0.200267 0.215863 -6.066900687582077 -12.853522836243359
	IQ2_XS code_codeparrot 0.174294 0.002979 100 512 0.184403 0.193624 -5.4820149346811125 -9.983266537206125
	IQ2_XS math_gsm8k 0.120991 0.002643 100 512 0.132848 0.146175 -8.925237865831626 -17.228664272276383
	IQ2_XS multilingual_mc4_de 0.166814 0.00467 25 512 0.158851 0.185316 5.012873699252762 -9.984027283127206
	IQ2_XS multilingual_mc4_fr 0.213379 0.005505 25 512 0.227306 0.241407 -6.126983009687381 -11.610268136383784
	IQ2_XS multilingual_mc4_es 0.119114 0.004094 25 512 0.126496 0.135836 -5.835757652415885 -12.310433169410185
	IQ2_XS multilingual_mc4_zh 0.264923 0.005239 25 512 0.296037 0.289135 -10.510172714897115 -8.373942967817783
	IQ2_XS fresh_c4_en_shard6 0.186271 0.001944 100 512 0.198573 -6.195202771776631
	Q2_0 code_codeparrot 0.235256 0.003868 100 512 0.219545 0.228021 7.156163884397282 3.1729533683301003
	Q2_0 fresh_c4_en_shard6 0.236228 0.002652 100 512 0.218501 8.113006347797036
	Q2_0 math_gsm8k 0.149809 0.003194 100 512 0.163066 0.202867 -8.129836998515938 -26.15408124534794
	Q2_0 multilingual_mc4_de 0.219444 0.00608 25 512 0.192854 0.248268 13.78763209474525 -11.610034317753392
	Q2_0 multilingual_mc4_es 0.148757 0.004586 25 512 0.144779 0.171527 2.7476360521899057 -13.274878007544011
	Q2_0 multilingual_mc4_fr 0.300467 0.007617 25 512 0.2717 0.337115 10.587780640412214 -10.871067736529083
	Q2_0 multilingual_mc4_zh 0.385924 0.007076 25 512 0.446938 0.376247 -13.651557934210112 2.5719806403772028
	Q2_0 prose_c4 0.234242 0.00257 100 512 0.218335 0.270309 7.285593239746269 -13.34287796558754
	IQ3_XXS prose_c4 0.116077 0.001601 100 512 0.114982 0.125842 0.9523229722913085 -7.7597304556507485
	IQ3_XXS code_codeparrot 0.118707 0.002266 100 512 0.117015 0.122811 1.4459684655813376 -3.3417202042162475
	IQ3_XXS math_gsm8k 0.086821 0.002149 100 512 0.094208 0.103453 -7.841159986413048 -16.076865823127417
	IQ3_XXS multilingual_mc4_de 0.1091 0.003632 25 512 0.104781 0.12331 4.12193050266747 -11.523801800340605
	IQ3_XXS multilingual_mc4_fr 0.133624 0.003993 25 512 0.130922 0.152166 2.063824261774183 -12.18537649672069
	IQ3_XXS multilingual_mc4_es 0.073681 0.002812 25 512 0.073858 0.080745 -0.23964905629721978 -8.748529320700971
	IQ3_XXS multilingual_mc4_zh 0.174102 0.004177 25 512 0.183406 0.169308 -5.072898378460899 2.831525976327187