Instructions to use rao-studios/Inkling-2-Mini with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use rao-studios/Inkling-2-Mini with MLX:
# Make sure mlx-lm is installed # pip install --upgrade mlx-lm # Generate text with mlx-lm from mlx_lm import load, generate model, tokenizer = load("rao-studios/Inkling-2-Mini") prompt = "Write a story about Einstein" messages = [{"role": "user", "content": prompt}] prompt = tokenizer.apply_chat_template( messages, add_generation_prompt=True ) text = generate(model, tokenizer, prompt=prompt, verbose=True) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Pi
How to use rao-studios/Inkling-2-Mini with Pi:
Start the MLX server
# Install MLX LM: uv tool install mlx-lm # Start a local OpenAI-compatible server: mlx_lm.server --model "rao-studios/Inkling-2-Mini"
Configure the model in Pi
# Install Pi: npm install -g @earendil-works/pi-coding-agent # Add to ~/.pi/agent/models.json: { "providers": { "mlx-lm": { "baseUrl": "http://localhost:8080/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "rao-studios/Inkling-2-Mini" } ] } } }Run Pi
# Start Pi in your project directory: pi
- MLX LM
How to use rao-studios/Inkling-2-Mini with MLX LM:
Generate or start a chat session
# Install MLX LM uv tool install mlx-lm # Interactive chat REPL mlx_lm.chat --model "rao-studios/Inkling-2-Mini"
Run an OpenAI-compatible server
# Install MLX LM uv tool install mlx-lm # Start the server mlx_lm.server --model "rao-studios/Inkling-2-Mini" # Calling the OpenAI-compatible server with curl curl -X POST "http://localhost:8080/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "rao-studios/Inkling-2-Mini", "messages": [ {"role": "user", "content": "Hello"} ] }' - Hermes Agent
How to use rao-studios/Inkling-2-Mini with Hermes Agent:
Start the MLX server
# Install MLX LM: uv tool install mlx-lm # Start a local OpenAI-compatible server: mlx_lm.server --model "rao-studios/Inkling-2-Mini"
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 rao-studios/Inkling-2-Mini
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use rao-studios/Inkling-2-Mini with OpenClaw:
Start the MLX server
# Install MLX LM: uv tool install mlx-lm # Start a local OpenAI-compatible server: mlx_lm.server --model "rao-studios/Inkling-2-Mini"
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 "rao-studios/Inkling-2-Mini" \ --custom-provider-id mlx-lm \ --custom-compatibility openai \ --custom-text-input \ --accept-risk \ --skip-health
Run OpenClaw
openclaw agent --local --agent main --message "Hello from Hugging Face"
Download README.md from rao-studios/Inkling-2-Mini: direct link, hf CLI and curl.
- Browser
- Download file 5.13 kB
-
https://huggingface.co/rao-studios/Inkling-2-Mini/resolve/main/README.md
- Command line
-
hf download hf://rao-studios/Inkling-2-Mini/README.md
-
curl -L -o README.md https://huggingface.co/rao-studios/Inkling-2-Mini/resolve/main/README.md
license: apache-2.0
base_model: thinkingmachines/Inkling-2-Mini
pipeline_tag: text-generation
library_name: mlx
tags:
- mlx
- inkling2_loop
- code
- craft
- mirror
rao-studios/Inkling-2-Mini
Rao Studios' mirror of thinkingmachines/Inkling-2-Mini at commit ed40e7da625f594fc9c4990f5f66be24873c22d7. The weights,
tokenizer, chat template and configuration are byte-for-byte that repository's; nothing was re-quantized or edited.
This card and LICENSE (the Apache License 2.0 text from https://www.apache.org/licenses/LICENSE-2.0.txt: thinkingmachines/Inkling-2-Mini declares license: apache-2.0 in its card at ed40e7da625f594fc9c4990f5f66be24873c22d7 and ships no LICENSE file) were added.
It exists so every install of Craft fetches the same bytes from a repository Rao controls: Craft's onboarding recommends it by this Mac's memory, and pins this repository at one commit.
Craft
Craft is a coding app that runs on your Mac: the model and the index of your project stay on the machine. Craft offers it on Macs with 48 GB of memory or more, and recommends it from 48 GB up.
Craft builds a whole iPhone app from an empty folder in one turn. The model plans, then calls fifteen agents from Craft's store in order: the project, the look, the mark, the typed client, the mock world, each screen's kit, the navigation, the tests and the screenshots. Then it builds, tests and shoots. Measured twice, the app built, its tests passed, and all 62 of the original app's screens matched it, light and dark: the quality Claude Opus reached on the same app.
Those runs used Qwopus 3.5 122B on an M4 Max with 128 GB (2026-11-16), not this model. In Craft, Settings › Guide walks through the run, says which model and Mac it needs, and sets Craft up for it. More at craft.rao.nyc.
Lineage
- thinkingmachines/Inkling-2-Mini, by Thinking Machines Lab (Apache-2.0).
- thinkingmachines/Inkling-2-Mini: the published checkpoint itself (NVFP4 and MXFP8 experts, BF16 elsewhere), which MLX reads as it is — the files here.
Shape (from config.json)
| Architecture | inkling2_loop, 24 layers |
| Quantization | NVFP4, as published (NVIDIA ModelOpt; the tensors say each layer's format) |
| Weights | 19.5 GB of safetensors, 1,244 tensors |
| Context | 1,048,576 tokens |
| Tools | Inkling frames: the chat template declares every tool's JSON schema in one system frame, and the model answers with a frame per call: the tool's name, then a JSON object of the name and its args |
A call, as the model writes it:
<|message_model|>edit_file<|content_invoke_tool_json|>{"name":"edit_file","args":{"new_string":"print(\"hello\")","old_string":"print(\"hi\")","path":"Sources/App/main.swift"}}<|end_message|>
Safety pass
Run by Craft's Scripts/release/mirror-model.py on 2026-11-20, before upload:
- Every file is one an MLX model needs; no pickle format and no native code was in the source.
- Every weight file is safetensors, its header read by hand: known dtypes, tensors that tile the file exactly, the same tensor names as the index.
- Every file matches the SHA-256 the Hub recorded for it at
ed40e7da625f594fc9c4990f5f66be24873c22d7. - No
auto_map(remote code) in the config or the tokenizer config; a chat template is present. hf_quant_config.jsonwas dropped: the quantizer's per-layer notes (NVIDIA ModelOpt): the tensors' own shapes and dtypes say each layer's format.mtp.safetensorswas dropped: the multi-token-prediction head, for speculative decoding: Craft's engine decodes one token at a time.processor_config.jsonwas dropped: the multimodal processor's settings: Craft reads text only.tiktoken/tokenizer.modelwas dropped: the vocabulary again, in tiktoken's format: Craft reads tokenizer.json.
| File | Bytes | SHA-256 |
|---|---|---|
chat_template.jinja |
6,868 | 53a9035f3255945704b5857657cfb00c1165090c0641c4f782a0cbf268cc16dc |
config.json |
2,722 | a7a349601f0984c4abf999c480ef775d8567d21f5f84b4e8a3e035b44f288dc2 |
generation_config.json |
98 | a08737c07a65a8fdf69f7cf086576210e5aad4b241437090b26d7b0c4f7905f7 |
model-00001-of-00001.safetensors |
19,526,019,168 | 65e60f51aa1284d4fb022584908c315270334d991828bb774af60584523539d1 |
model.safetensors.index.json |
109,300 | c1631065b7b00787993522dddc66a68b3abee869192977fb3dcb796e63bc5838 |
special_tokens_map.json |
529 | c16f44b3594563d82743ddb0417a2be1bfe3e2000dfad2da4b8f32554593e1a0 |
tokenizer.json |
26,178,678 | 7f332727f9a3f093dd452a39cc978e6757627e5dad1b0673aa4e75174f236dd6 |
tokenizer_config.json |
13,235 | bf09342d285139fd37ce10c70878af1d52cb390e9901e10248654293a80ee636 |
Use with mlx
Craft loads it through Frigate, which reads inkling2_loop checkpoints as published; mlx-lm reads it from the version that adds the model type.