Instructions to use KiwiMate/KiwiMate-Small-Preview with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use KiwiMate/KiwiMate-Small-Preview 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 KiwiMate/KiwiMate-Small-Preview:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf KiwiMate/KiwiMate-Small-Preview:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf KiwiMate/KiwiMate-Small-Preview:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf KiwiMate/KiwiMate-Small-Preview: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 KiwiMate/KiwiMate-Small-Preview:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf KiwiMate/KiwiMate-Small-Preview: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 KiwiMate/KiwiMate-Small-Preview:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf KiwiMate/KiwiMate-Small-Preview:Q4_K_M

Use Docker

docker model run hf.co/KiwiMate/KiwiMate-Small-Preview:Q4_K_M

LM Studio
Jan

vLLM

How to use KiwiMate/KiwiMate-Small-Preview with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "KiwiMate/KiwiMate-Small-Preview"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "KiwiMate/KiwiMate-Small-Preview",
		"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/KiwiMate/KiwiMate-Small-Preview:Q4_K_M

Ollama
How to use KiwiMate/KiwiMate-Small-Preview with Ollama:
```
ollama run hf.co/KiwiMate/KiwiMate-Small-Preview:Q4_K_M
```

Unsloth Studio

How to use KiwiMate/KiwiMate-Small-Preview with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for KiwiMate/KiwiMate-Small-Preview to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for KiwiMate/KiwiMate-Small-Preview to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for KiwiMate/KiwiMate-Small-Preview to start chatting

How to use KiwiMate/KiwiMate-Small-Preview with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf KiwiMate/KiwiMate-Small-Preview:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "KiwiMate/KiwiMate-Small-Preview:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

OpenClaw new

How to use KiwiMate/KiwiMate-Small-Preview with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf KiwiMate/KiwiMate-Small-Preview: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 "KiwiMate/KiwiMate-Small-Preview: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"

Docker Model Runner
How to use KiwiMate/KiwiMate-Small-Preview with Docker Model Runner:
```
docker model run hf.co/KiwiMate/KiwiMate-Small-Preview:Q4_K_M
```

Lemonade

How to use KiwiMate/KiwiMate-Small-Preview with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull KiwiMate/KiwiMate-Small-Preview:Q4_K_M

Run and chat with the model

lemonade run user.KiwiMate-Small-Preview-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use KiwiMate/KiwiMate-Small-Preview with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf KiwiMate/KiwiMate-Small-Preview: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 KiwiMate/KiwiMate-Small-Preview:Q4_K_M

Run Hermes

hermes

Atomic Chat

KiwiMate-Small-Preview

KiwiMate-Small-Preview is the larger, multimodal model in the KiwiMate AI companion app's model family, fine-tuned for richer conversation and image understanding on the app's higher subscription tiers.

⚠️ Preview status: This is a prototype release. The name reflects its preview status — expect breaking changes, retraining, and behavioural shifts before a stable v1 release.

Model Details


Developed by	KiwiMate / KyleCodeKiwi
Base model	Qwen3.5-9B
Architecture	Qwen3.5 (`qwen3_5`)
Parameters	~9.65B
Modality	Multimodal (image-text-to-text)
Fine-tuning framework	Unsloth
License	Apache 2.0
Languages	English (with New Zealand English and Te Reo Māori vocabulary coverage)
Model class	`AutoModelForMultimodalLM`
Inference compatibility	vLLM-compatible

Intended Use

KiwiMate-Small-Preview is intended for the higher-tier, "smarter" conversational experience inside the KiwiMate app, providing:

Deeper general-purpose chat and assistant-style conversation than KiwiMate-Mini-Preview
Image understanding (e.g. user-uploaded photos within the app)
New Zealand cultural and "Kiwi" context awareness, plus light Te Reo Māori vocabulary
KiwiMate app-specific lore and identity content

It is not intended for high-stakes, medical, legal, or financial advice, and should not be treated as authoritative on Te Reo Māori or tikanga matters.

Training Data

Fine-tuned using the same category structure as the rest of the KiwiMate model family: NZ English, Te Reo Māori, KiwiMate Origin (app-specific lore/identity), NZ Fun Facts, and MiniGame Knowledge, alongside the base Qwen3.5-9B multimodal capabilities.

Files & Quantizations

Distributed as safetensors (full precision) and GGUF quantizations for flexible serving:

Format	Use case
F16	Highest fidelity, largest size
Q6_K	Near-lossless, smaller footprint
Q4_K_M	Balanced quality/size
Q2_K_L	Smallest footprint, lowest fidelity

Deployment

Served in production via a Hugging Face Inference Endpoint on an L40S GPU, fronted by a Supabase Edge Function (OpenAI-compatible proxy) that routes KiwiMate app traffic to this and other KiwiMate model endpoints behind a single API.

Known Limitations

An earlier deployment issue caused by a tokenizer_config.json incompatibility (TokenizersBackend → Qwen2TokenizerFast) was identified and resolved; deployments should pin a compatible tokenizer backend.
As with any 9–10B parameter multimodal model, image reasoning and fine factual detail can lag behind larger frontier models — it is tuned for a balance of capability and serving cost rather than maximum raw performance.