Instructions to use AtomicChat/Inkling-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AtomicChat/Inkling-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="AtomicChat/Inkling-GGUF",
	filename="IQ1_M-final/Inkling-Atomic-IQ1_M-00001-of-00006.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 AtomicChat/Inkling-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 AtomicChat/Inkling-GGUF:IQ1_M
# Run inference directly in the terminal:
llama cli -hf AtomicChat/Inkling-GGUF:IQ1_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf AtomicChat/Inkling-GGUF:IQ1_M
# Run inference directly in the terminal:
llama cli -hf AtomicChat/Inkling-GGUF:IQ1_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 AtomicChat/Inkling-GGUF:IQ1_M
# Run inference directly in the terminal:
./llama-cli -hf AtomicChat/Inkling-GGUF:IQ1_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 AtomicChat/Inkling-GGUF:IQ1_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf AtomicChat/Inkling-GGUF:IQ1_M

Use Docker

docker model run hf.co/AtomicChat/Inkling-GGUF:IQ1_M

LM Studio
Jan

vLLM

How to use AtomicChat/Inkling-GGUF with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/AtomicChat/Inkling-GGUF:IQ1_M

Ollama
How to use AtomicChat/Inkling-GGUF with Ollama:
```
ollama run hf.co/AtomicChat/Inkling-GGUF:IQ1_M
```

Unsloth Studio

How to use AtomicChat/Inkling-GGUF 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 AtomicChat/Inkling-GGUF 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 AtomicChat/Inkling-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for AtomicChat/Inkling-GGUF to start chatting

How to use AtomicChat/Inkling-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf AtomicChat/Inkling-GGUF:IQ1_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": "AtomicChat/Inkling-GGUF:IQ1_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use AtomicChat/Inkling-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 AtomicChat/Inkling-GGUF:IQ1_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 AtomicChat/Inkling-GGUF:IQ1_M

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use AtomicChat/Inkling-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf AtomicChat/Inkling-GGUF:IQ1_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 "AtomicChat/Inkling-GGUF:IQ1_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 AtomicChat/Inkling-GGUF with Docker Model Runner:
```
docker model run hf.co/AtomicChat/Inkling-GGUF:IQ1_M
```

Lemonade

How to use AtomicChat/Inkling-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull AtomicChat/Inkling-GGUF:IQ1_M

Run and chat with the model

lemonade run user.Inkling-GGUF-IQ1_M

List all available models

lemonade list

Base model: thinkingmachines/Inkling

Inkling (Thinking Machines Lab), self-quantized to GGUF by Atomic Chat. Built straight from Thinking Machines' original BF16 weights with a per-tensor importance matrix. Runs fully offline, including a 1-bit build that brings this 975B model down to 226 GB.

Highlights

975B-parameter MoE with 41B active: each token is routed to 6 of 256 experts, plus 2 shared experts active on every token, across a 66-layer decoder.
Context up to 1M tokens with a hybrid of local and global attention layers.
Natively multimodal base: the original model reasons over text, images and audio in a shared hidden space. This repo ships the text path.
Strong reasoning scores (Thinking Machines-reported, effort=0.99): AIME 2026 97.1, GPQA Diamond 87.2, SWEBench Verified 77.6.
Built to be fine-tuned: Thinking Machines positions Inkling as a base for domain adaptation, released under Apache 2.0.
Full imatrix quantization over a code corpus, including a 1-bit IQ1_M and an MXFP4 build with Q8 attention and routing.

These GGUFs are self-quantized from the original weights, not a repack. The importance matrix keeps low-bit quants closer to the full-precision model.

Always pass --jinja so the Inkling chat template (interleaved thinking and tool calls) is applied. Without it the model can emit malformed turns.

The inkling architecture is not yet in a mainline llama.cpp release. Until PR #25731 is merged, build llama.cpp from that PR (instructions below). Standard Ollama / LM Studio flows will work once support lands upstream.

This repo ships the text path only: no vision or audio projector (mmproj) is included. For multimodal use, run the original weights.

Model Overview

Property	Value
Base model	`thinkingmachines/Inkling`
Total / active parameters	975B total / 41B active
Layers	66
Experts	256 routed (top-6) + 2 shared, active on every token
Context length	up to 1M tokens
Architecture	Decoder-only Mixture-of-Experts, hybrid local/global attention, natively multimodal (text, image, audio in; text out)
This repo	GGUF quants (imatrix), text path: `Q8_0` reference, `MXFP4` with Q8 attention/routing, and a 1-bit `IQ1_M` (226 GB)

Scores are Thinking Machines' published results for the base thinkingmachines/Inkling, reported at thinking effort 0.99. Quantization preserves the large majority of this; low-bit builds trade some quality for size.

Choosing a quant

Quant	Size	Notes
`IQ1_M`	226 GB	Smallest. 1-bit imatrix build that makes a 975B model runnable on a single big-RAM server (about 226 GB plus context). Expect quality tradeoffs; reasoning still works.
`MXFP4`	514 GB	Recommended for quality. Expert FFN weights in the 4-bit MXFP4 block format, with attention, expert router and shared experts held at Q8_0.
`Q8_0`	1.01 TB	Reference quality, near-lossless. Also the substrate our importance matrix was computed on. For large multi-node or big-RAM setups.

Get started

Inkling needs a llama.cpp build with the inkling architecture (see Run in llama.cpp below). Then:

./build/bin/llama-server -hf AtomicChat/Inkling-GGUF:IQ1_M --jinja -c 8192

Or download a quant explicitly:

hf download AtomicChat/Inkling-GGUF --include "IQ1_M-final/*" --local-dir Inkling-GGUF
# "MXFP4/*" for 4-bit, "Q8_0/*" for the reference build

Best practices

Thinking Machines does not publish recommended sampler settings for local inference. Two things do matter:

Always pass --jinja. The Inkling template carries the model's interleaved thinking and tool-call blocks; without it output breaks.
Benchmark numbers above are reported at thinking effort 0.99. Inkling's thinking effort is adjustable, so shorter-thinking runs will score below the chart.

Run in llama.cpp

Inkling support lives in PR #25731 until it is merged upstream:

git clone https://github.com/ggml-org/llama.cpp
cd llama.cpp
gh pr checkout 25731
cmake -B build -DBUILD_SHARED_LIBS=OFF -DGGML_CUDA=ON
cmake --build build --config Release -j --target llama-cli llama-server

./build/bin/llama-server \
    -hf AtomicChat/Inkling-GGUF:MXFP4 \
    --jinja -ngl 99 -c 8192 -fa on

How these were made

Download thinkingmachines/Inkling (original BF16 weights, about 2 TB).
Convert to GGUF with llama.cpp built from PR #25731, which adds the inkling architecture.
Produce a Q8_0 reference and compute an importance matrix over an 18 MB code corpus (Linux, CPython, Rust and llama.cpp sources), 7,040 chunks of 512 tokens, with 93-99% expert activation coverage. The imatrix files are published in imatrix/.
Quantize with --imatrix: MXFP4 for expert FFNs with attention, router and shared experts at Q8_0, and IQ1_M with the same Q8 overlay for the smallest coherent build.