Instructions to use StationPC/Qwen3.5-4B-RKNN3-RK1828 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use StationPC/Qwen3.5-4B-RKNN3-RK1828 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 StationPC/Qwen3.5-4B-RKNN3-RK1828
# Run inference directly in the terminal:
llama cli -hf StationPC/Qwen3.5-4B-RKNN3-RK1828

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf StationPC/Qwen3.5-4B-RKNN3-RK1828
# Run inference directly in the terminal:
llama cli -hf StationPC/Qwen3.5-4B-RKNN3-RK1828

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 StationPC/Qwen3.5-4B-RKNN3-RK1828
# Run inference directly in the terminal:
./build/bin/llama cli -hf StationPC/Qwen3.5-4B-RKNN3-RK1828

Use Docker

docker model run hf.co/StationPC/Qwen3.5-4B-RKNN3-RK1828

Llama new
LM Studio
Jan

vLLM

How to use StationPC/Qwen3.5-4B-RKNN3-RK1828 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "StationPC/Qwen3.5-4B-RKNN3-RK1828"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "StationPC/Qwen3.5-4B-RKNN3-RK1828",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/StationPC/Qwen3.5-4B-RKNN3-RK1828

Ollama
How to use StationPC/Qwen3.5-4B-RKNN3-RK1828 with Ollama:
```
ollama run hf.co/StationPC/Qwen3.5-4B-RKNN3-RK1828
```
Unsloth Desktop

How to use StationPC/Qwen3.5-4B-RKNN3-RK1828 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf StationPC/Qwen3.5-4B-RKNN3-RK1828

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": "StationPC/Qwen3.5-4B-RKNN3-RK1828"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use StationPC/Qwen3.5-4B-RKNN3-RK1828 with Docker Model Runner:
```
docker model run hf.co/StationPC/Qwen3.5-4B-RKNN3-RK1828
```

Lemonade

How to use StationPC/Qwen3.5-4B-RKNN3-RK1828 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull StationPC/Qwen3.5-4B-RKNN3-RK1828

Run and chat with the model

lemonade run user.Qwen3.5-4B-RKNN3-RK1828-{{QUANT_TAG}}

List all available models

lemonade list

Hermes Agent

How to use StationPC/Qwen3.5-4B-RKNN3-RK1828 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf StationPC/Qwen3.5-4B-RKNN3-RK1828

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 StationPC/Qwen3.5-4B-RKNN3-RK1828

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use StationPC/Qwen3.5-4B-RKNN3-RK1828 with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf StationPC/Qwen3.5-4B-RKNN3-RK1828

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 "StationPC/Qwen3.5-4B-RKNN3-RK1828" \
  --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"

StationPC commited on Sep 29

Commit

c091d93

verified ·

1 Parent(s): d4d7079

Update Qwen3.5-4B RKNN3 model artifacts

Browse files

Files changed (7) hide show

.gitattributes +4 -0
.ms_upload_cache +1 -0
Qwen3.5-4B-16384.rknn → llm_Qwen3.5-4B-16384.rknn +2 -2
Qwen3.5-4B.weight → llm_Qwen3.5-4B.weight +2 -2
model.toml +1 -0
vision_Qwen3.5-4B.rknn +3 -0
vision_Qwen3.5-4B.weight +3 -0

.gitattributes CHANGED Viewed

@@ -50,3 +50,7 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 "/tokenizer.json" filter=lfs diff=lfs merge=lfs -textQwen3.5-4B-16384.rknn filter=lfs diff=lfs merge=lfs -text
 Qwen3.5-4B.weight filter=lfs diff=lfs merge=lfs -text
 tokenizer.json filter=lfs diff=lfs merge=lfs -text

 "/tokenizer.json" filter=lfs diff=lfs merge=lfs -textQwen3.5-4B-16384.rknn filter=lfs diff=lfs merge=lfs -text
 Qwen3.5-4B.weight filter=lfs diff=lfs merge=lfs -text
 tokenizer.json filter=lfs diff=lfs merge=lfs -text
+llm_Qwen3.5-4B-16384.rknn filter=lfs diff=lfs merge=lfs -text
+llm_Qwen3.5-4B.weight filter=lfs diff=lfs merge=lfs -text
+vision_Qwen3.5-4B.rknn filter=lfs diff=lfs merge=lfs -text
+vision_Qwen3.5-4B.weight filter=lfs diff=lfs merge=lfs -text

.ms_upload_cache ADDED Viewed

	@@ -0,0 +1 @@

+ {"version": 3, "repo_id": "StationPC/Qwen3.5-4B-RKNN3-RK1828", "files": {"model.toml|1790665664.6347823|224": {"hash": "015efbabc4d360211dffe55fab660fa84c5c19ca76f35fd4420eea4fff978e01", "size": 224, "status": "c"}, "vision_Qwen3.5-4B.rknn|1790665632.1351116|5226288": {"hash": "212bb4e1caa24395b00904141a44d0551727f72ff2fd1b6460682d09667c9c2d", "size": 5226288, "status": "c"}, "llm_Qwen3.5-4B-16384.rknn|1790665099.947504|42276160": {"hash": "ee6680de1d867a14e8b12bd4466c4cfb13e27794f9db4bc6bd6b5c750530c1a4", "size": 42276160, "status": "c"}, "vision_Qwen3.5-4B.weight|1790665664.364785|196952064": {"hash": "4622ccd2bb454c3c29a97561b7c909f7e44842150ea782fd895743678cdc8759", "size": 196952064, "status": "c"}, "llm_Qwen3.5-4B.weight|1790665631.2511203|2647439872": {"hash": "af35a07fddab616ebe7dfb9175e6aa8c5d725448981b6e5129b8b59ba4e6f0ae", "size": 2647439872, "status": "c"}}}

Qwen3.5-4B-16384.rknn → llm_Qwen3.5-4B-16384.rknn RENAMED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9cec13327256418fbfbb5ad2f13a7b59408e3ddcbba930eec967998c52671fd9
-size 42487440

 version https://git-lfs.github.com/spec/v1
+oid sha256:ee6680de1d867a14e8b12bd4466c4cfb13e27794f9db4bc6bd6b5c750530c1a4
+size 42276160

Qwen3.5-4B.weight → llm_Qwen3.5-4B.weight RENAMED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b55da072ea3737eb8c467f3f48e2873a7d3eadbb4e594425272dcbd2436f6bb
-size 2647438336

 version https://git-lfs.github.com/spec/v1
+oid sha256:af35a07fddab616ebe7dfb9175e6aa8c5d725448981b6e5129b8b59ba4e6f0ae
+size 2647439872

model.toml CHANGED Viewed

@@ -3,6 +3,7 @@ platform = "rknn3"
 kind = "chat"
 chip_type = "rk1828"
 quantized_dtype = "w4a16"
 tool_call_parser_class = "qwen3_5"
 [model.default_params]

 kind = "chat"
 chip_type = "rk1828"
 quantized_dtype = "w4a16"
+model_type = "qwen3_5"
 tool_call_parser_class = "qwen3_5"
 [model.default_params]

vision_Qwen3.5-4B.rknn ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:212bb4e1caa24395b00904141a44d0551727f72ff2fd1b6460682d09667c9c2d
+size 5226288

vision_Qwen3.5-4B.weight ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:4622ccd2bb454c3c29a97561b7c909f7e44842150ea782fd895743678cdc8759
+size 196952064