Instructions to use JasonIr/typurr-sketch-0.8b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use JasonIr/typurr-sketch-0.8b with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="JasonIr/typurr-sketch-0.8b",
	filename="typurr-sketch-0.8b-q6_k.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use JasonIr/typurr-sketch-0.8b 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 JasonIr/typurr-sketch-0.8b:Q6_K
# Run inference directly in the terminal:
llama cli -hf JasonIr/typurr-sketch-0.8b:Q6_K

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf JasonIr/typurr-sketch-0.8b:Q6_K
# Run inference directly in the terminal:
llama cli -hf JasonIr/typurr-sketch-0.8b:Q6_K

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 JasonIr/typurr-sketch-0.8b:Q6_K
# Run inference directly in the terminal:
./llama-cli -hf JasonIr/typurr-sketch-0.8b:Q6_K

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 JasonIr/typurr-sketch-0.8b:Q6_K
# Run inference directly in the terminal:
./build/bin/llama-cli -hf JasonIr/typurr-sketch-0.8b:Q6_K

Use Docker

docker model run hf.co/JasonIr/typurr-sketch-0.8b:Q6_K

LM Studio
Jan

vLLM

How to use JasonIr/typurr-sketch-0.8b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "JasonIr/typurr-sketch-0.8b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "JasonIr/typurr-sketch-0.8b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/JasonIr/typurr-sketch-0.8b:Q6_K

Ollama
How to use JasonIr/typurr-sketch-0.8b with Ollama:
```
ollama run hf.co/JasonIr/typurr-sketch-0.8b:Q6_K
```

Unsloth Studio

How to use JasonIr/typurr-sketch-0.8b 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 JasonIr/typurr-sketch-0.8b 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 JasonIr/typurr-sketch-0.8b to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for JasonIr/typurr-sketch-0.8b to start chatting

How to use JasonIr/typurr-sketch-0.8b with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf JasonIr/typurr-sketch-0.8b:Q6_K

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": "JasonIr/typurr-sketch-0.8b:Q6_K"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use JasonIr/typurr-sketch-0.8b with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf JasonIr/typurr-sketch-0.8b:Q6_K

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 JasonIr/typurr-sketch-0.8b:Q6_K

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use JasonIr/typurr-sketch-0.8b with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf JasonIr/typurr-sketch-0.8b:Q6_K

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 "JasonIr/typurr-sketch-0.8b:Q6_K" \
  --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 JasonIr/typurr-sketch-0.8b with Docker Model Runner:
```
docker model run hf.co/JasonIr/typurr-sketch-0.8b:Q6_K
```

Lemonade

How to use JasonIr/typurr-sketch-0.8b with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull JasonIr/typurr-sketch-0.8b:Q6_K

Run and chat with the model

lemonade run user.typurr-sketch-0.8b-Q6_K

List all available models

lemonade list

typurr-sketch-0.8b — the Sketcher

The model that cleans your speech while you're still talking.

Typurr feeds it clauses from a streaming recognizer as you speak; it strips fillers, resolves self-corrections, punctuates, capitalizes, and formats spoken numbers — so the finished text exists before you release the key.

in (spoken)	out
"um so basically can you send me the uh the report"	"Can you send me the report"
"it costs ten dollars, uh, per seat and dana no wait marcus should get the invoice"	"It costs $10 per seat and Marcus should get the invoice."

Numbers

metric (held-out dictation)	base Qwen3.5-0.8B	this model
exact match	0.0%	90.7%
filler leaks	63%	0%
content lost	2.7%	0%

~150 ms per clause on a laptop GPU (q8_0, llama.cpp). Trained on 58.8k synthetic (mangled-speech → clean-text) pairs from Typurr's data engine.

Coupling note: tuned to Typurr's exact system prompt (prompts.rs::SKETCH_RULES); with other prompts it still works, worse. Inside Typurr it runs behind a fidelity audit — outputs that invent names or numbers are caught and redone by a larger model.

Typurr — speak, it types. Nothing leaves your machine.

A Windows dictation app and voice assistant that runs entirely on your own hardware: hold a hotkey, talk, release — finished text lands at your cursor in any app. No account, no telemetry, no audio in anyone's cloud.

Instant finish — its models clean your speech while you talk; the text is ready the moment you release the key
Speaks & listens — neural voice read-backs, review-before-send by voice, "typurr do…" compound commands, wake word
Learns you — your vocabulary, your corrections, your style; all in plain files on your disk
Gives AI agents a voice — local MCP server: your agents can speak, ask you questions aloud, and type at your cursor

Get it: typurr.com · GitHub · scoop install https://raw.githubusercontent.com/typurrapp/typurr/main/typurr.json