Instructions to use gabriellarson/Skywork-SWE-32B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use gabriellarson/Skywork-SWE-32B-GGUF with Transformers:

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

pipe = pipeline("text-generation", model="gabriellarson/Skywork-SWE-32B-GGUF")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("gabriellarson/Skywork-SWE-32B-GGUF", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use gabriellarson/Skywork-SWE-32B-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 gabriellarson/Skywork-SWE-32B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf gabriellarson/Skywork-SWE-32B-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf gabriellarson/Skywork-SWE-32B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf gabriellarson/Skywork-SWE-32B-GGUF: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 gabriellarson/Skywork-SWE-32B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf gabriellarson/Skywork-SWE-32B-GGUF: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 gabriellarson/Skywork-SWE-32B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf gabriellarson/Skywork-SWE-32B-GGUF:Q4_K_M

Use Docker

docker model run hf.co/gabriellarson/Skywork-SWE-32B-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use gabriellarson/Skywork-SWE-32B-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "gabriellarson/Skywork-SWE-32B-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": "gabriellarson/Skywork-SWE-32B-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/gabriellarson/Skywork-SWE-32B-GGUF:Q4_K_M

SGLang

How to use gabriellarson/Skywork-SWE-32B-GGUF 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 "gabriellarson/Skywork-SWE-32B-GGUF" \
    --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": "gabriellarson/Skywork-SWE-32B-GGUF",
		"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 "gabriellarson/Skywork-SWE-32B-GGUF" \
        --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": "gabriellarson/Skywork-SWE-32B-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use gabriellarson/Skywork-SWE-32B-GGUF with Ollama:
```
ollama run hf.co/gabriellarson/Skywork-SWE-32B-GGUF:Q4_K_M
```
Unsloth Desktop

How to use gabriellarson/Skywork-SWE-32B-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf gabriellarson/Skywork-SWE-32B-GGUF:Q4_K_M

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": "gabriellarson/Skywork-SWE-32B-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use gabriellarson/Skywork-SWE-32B-GGUF with Docker Model Runner:
```
docker model run hf.co/gabriellarson/Skywork-SWE-32B-GGUF:Q4_K_M
```

Lemonade

How to use gabriellarson/Skywork-SWE-32B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull gabriellarson/Skywork-SWE-32B-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Skywork-SWE-32B-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use gabriellarson/Skywork-SWE-32B-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 gabriellarson/Skywork-SWE-32B-GGUF: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 gabriellarson/Skywork-SWE-32B-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use gabriellarson/Skywork-SWE-32B-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf gabriellarson/Skywork-SWE-32B-GGUF:Q4_K_M

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 "gabriellarson/Skywork-SWE-32B-GGUF:Q4_K_M" \
  --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"

gabriellarson commited on Jun 19, 2025

Commit

b3b92ca

verified ·

1 Parent(s): 37a2b36

Upload folder using huggingface_hub

Browse files

Files changed (25) hide show

.gitattributes +24 -0
Skywork-SWE-32B-IQ1_M.gguf +3 -0
Skywork-SWE-32B-IQ1_S.gguf +3 -0
Skywork-SWE-32B-IQ2_M.gguf +3 -0
Skywork-SWE-32B-IQ2_S.gguf +3 -0
Skywork-SWE-32B-IQ2_XS.gguf +3 -0
Skywork-SWE-32B-IQ2_XXS.gguf +3 -0
Skywork-SWE-32B-IQ3_M.gguf +3 -0
Skywork-SWE-32B-IQ3_S.gguf +3 -0
Skywork-SWE-32B-IQ3_XS.gguf +3 -0
Skywork-SWE-32B-IQ3_XXS.gguf +3 -0
Skywork-SWE-32B-IQ4_XS.gguf +3 -0
Skywork-SWE-32B-Q2_K.gguf +3 -0
Skywork-SWE-32B-Q2_K_S.gguf +3 -0
Skywork-SWE-32B-Q3_K_L.gguf +3 -0
Skywork-SWE-32B-Q3_K_M.gguf +3 -0
Skywork-SWE-32B-Q3_K_S.gguf +3 -0
Skywork-SWE-32B-Q4_0.gguf +3 -0
Skywork-SWE-32B-Q4_K_M.gguf +3 -0
Skywork-SWE-32B-Q4_K_S.gguf +3 -0
Skywork-SWE-32B-Q5_0.gguf +3 -0
Skywork-SWE-32B-Q5_K_M.gguf +3 -0
Skywork-SWE-32B-Q5_K_S.gguf +3 -0
Skywork-SWE-32B-Q6_K.gguf +3 -0
Skywork-SWE-32B-Q8_0.gguf +3 -0

.gitattributes CHANGED Viewed

@@ -33,3 +33,27 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text

 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+Skywork-SWE-32B-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text
+Skywork-SWE-32B-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text
+Skywork-SWE-32B-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text
+Skywork-SWE-32B-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text
+Skywork-SWE-32B-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text
+Skywork-SWE-32B-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text
+Skywork-SWE-32B-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
+Skywork-SWE-32B-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text
+Skywork-SWE-32B-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text
+Skywork-SWE-32B-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text
+Skywork-SWE-32B-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
+Skywork-SWE-32B-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+Skywork-SWE-32B-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Skywork-SWE-32B-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+Skywork-SWE-32B-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Skywork-SWE-32B-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Skywork-SWE-32B-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+Skywork-SWE-32B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Skywork-SWE-32B-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Skywork-SWE-32B-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+Skywork-SWE-32B-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Skywork-SWE-32B-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Skywork-SWE-32B-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+Skywork-SWE-32B-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text

Skywork-SWE-32B-IQ1_M.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:f21bea9065c7d6817c677151cd38a011ea2cecb92b8f24c357d4016758c2ac43
+size 7932160640

Skywork-SWE-32B-IQ1_S.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:36e21ae02fe8f16c1d327c105747daca314052a66da40f4de87454fe47cebd9c
+size 7274506880

Skywork-SWE-32B-IQ2_M.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:4be2891dec1c9ddc7f4ae080f4ad95d267223c934b63641ab12e3815cf6d8f43
+size 11264440960

Skywork-SWE-32B-IQ2_S.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:8daa6b91e6e5ee1d694293e5bb122278b934b97177db416338cf7296f56e3e15
+size 10387569280

Skywork-SWE-32B-IQ2_XS.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:991b5019a985c911a53405a04159a6bb0ff08b59c923a3d5ab1ba128a13c6103
+size 9957550720

Skywork-SWE-32B-IQ2_XXS.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:e4c98c6f9af0b8c0889ef3b3f3752ee8edc5577134baf4672b8ff1837eb694b4
+size 9028250240

Skywork-SWE-32B-IQ3_M.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:c58e7ceb2a1e40060da429e194b44e0df19eb60ba19a175a7767fc84141dcf2c
+size 14810122880

Skywork-SWE-32B-IQ3_S.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:8159a9df2c7dc2dce273d9ae59e51e105841b4348ed08bfb1e28d2b1f9d44726
+size 14436895360

Skywork-SWE-32B-IQ3_XS.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:12eb6e24df050157152a2e479b4cefe51442d99469a4caf0b6d2687ef47fe70f
+size 13705513600

Skywork-SWE-32B-IQ3_XXS.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:35364e14932fefa75d7fc2ebb0cf9c9564495e33e45683eff390fcd36002a9ee
+size 12839271040

Skywork-SWE-32B-IQ4_XS.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:c5019c173e33567be107fe02bae70220d264f976479d0abe4b6070be1cade96e
+size 17693153920

Skywork-SWE-32B-Q2_K.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:ca38ecfc44b4866d887fa6838dc82ec3a774ebc00e4efab97816cf06445aa958
+size 12313098880

Skywork-SWE-32B-Q2_K_S.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:2bef19b858cdd9e7a4945e3e174f2c668682c1e48848f355f69b1dd6f4cfee85
+size 11488000640

Skywork-SWE-32B-Q3_K_L.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:e1d2e109da54db419b59fa0c3682ae837a7060106ebdd28d64736c22af718419
+size 17247079040

Skywork-SWE-32B-Q3_K_M.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:1f3b3765c807e7948ae21de7985581e8819cf577aafdf5592e12ea45d6e754ba
+size 15935048320

Skywork-SWE-32B-Q3_K_S.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:0acc94e50a097f87bd4d6d970c6cf869067916a05728c23ac7f4824dad36c36e
+size 14392330880

Skywork-SWE-32B-Q4_0.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:9a4c54e9d9d216782edd689527117ebc4fb64df641f3080af37882349d01c6ab
+size 18711009920

Skywork-SWE-32B-Q4_K_M.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:599a59d928144193ca84b37c306174cc24ffa0b656097c0913028a73f78ac138
+size 19851336320

Skywork-SWE-32B-Q4_K_S.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:b853aec4079e6f3b1ec7ba9060effdb9073db352fc462bfdda6f7ce3ec1fa309
+size 18784410240

Skywork-SWE-32B-Q5_0.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:22d410a1832c91f34fdf0f12314cb32d57fdb90653f7378accfd3c8dfe9c090a
+size 22709033600

Skywork-SWE-32B-Q5_K_M.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:e69105551c8cac182bee14a419de4696cbce3659c9c4eea8ba64344b68bf8ff2
+size 23262157440

Skywork-SWE-32B-Q5_K_S.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:8d2ac1241797c2308ad4e5c176e83e1eb77ef6f9b75e1011245cb75caa7bbded
+size 22638254720

Skywork-SWE-32B-Q6_K.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:aac4042e8a457b861798451462832660b49b97c3fbb6ce0405bd5011368bc0d1
+size 26886154880

Skywork-SWE-32B-Q8_0.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:2bdcd89d53c8385dcde96135552f8191ee6b7fd4477e880979c1b88dc9222145
+size 34820885120