Instructions to use cebopp1/inkling-tiny-reasoning-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use cebopp1/inkling-tiny-reasoning-v1 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("cebopp1/inkling-tiny-reasoning-v1")

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

llama.cpp

How to use cebopp1/inkling-tiny-reasoning-v1 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 cebopp1/inkling-tiny-reasoning-v1:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf cebopp1/inkling-tiny-reasoning-v1:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf cebopp1/inkling-tiny-reasoning-v1:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf cebopp1/inkling-tiny-reasoning-v1: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 cebopp1/inkling-tiny-reasoning-v1:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf cebopp1/inkling-tiny-reasoning-v1: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 cebopp1/inkling-tiny-reasoning-v1:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf cebopp1/inkling-tiny-reasoning-v1:Q4_K_M

Use Docker

docker model run hf.co/cebopp1/inkling-tiny-reasoning-v1:Q4_K_M

LM Studio
Jan

vLLM

How to use cebopp1/inkling-tiny-reasoning-v1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "cebopp1/inkling-tiny-reasoning-v1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "cebopp1/inkling-tiny-reasoning-v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/cebopp1/inkling-tiny-reasoning-v1:Q4_K_M

Ollama
How to use cebopp1/inkling-tiny-reasoning-v1 with Ollama:
```
ollama run hf.co/cebopp1/inkling-tiny-reasoning-v1:Q4_K_M
```

Unsloth Studio

How to use cebopp1/inkling-tiny-reasoning-v1 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 cebopp1/inkling-tiny-reasoning-v1 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 cebopp1/inkling-tiny-reasoning-v1 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for cebopp1/inkling-tiny-reasoning-v1 to start chatting

How to use cebopp1/inkling-tiny-reasoning-v1 with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "cebopp1/inkling-tiny-reasoning-v1"

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": "cebopp1/inkling-tiny-reasoning-v1"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

MLX LM

How to use cebopp1/inkling-tiny-reasoning-v1 with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "cebopp1/inkling-tiny-reasoning-v1"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "cebopp1/inkling-tiny-reasoning-v1"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "cebopp1/inkling-tiny-reasoning-v1",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Docker Model Runner
How to use cebopp1/inkling-tiny-reasoning-v1 with Docker Model Runner:
```
docker model run hf.co/cebopp1/inkling-tiny-reasoning-v1:Q4_K_M
```

Lemonade

How to use cebopp1/inkling-tiny-reasoning-v1 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull cebopp1/inkling-tiny-reasoning-v1:Q4_K_M

Run and chat with the model

lemonade run user.inkling-tiny-reasoning-v1-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use cebopp1/inkling-tiny-reasoning-v1 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 "cebopp1/inkling-tiny-reasoning-v1"

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 cebopp1/inkling-tiny-reasoning-v1

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use cebopp1/inkling-tiny-reasoning-v1 with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "cebopp1/inkling-tiny-reasoning-v1"

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 "cebopp1/inkling-tiny-reasoning-v1" \
  --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"

inkling-tiny-reasoning-v1

Research preview. It performs the style of reasoning, but the content is unreliable. This ~8B-ish model (aggressively pruned + LoRA-distilled) produces convincing chain-of-thought — <think> blocks, "let me think carefully", "but wait", multi-step hedging — but it routinely confabulates: it hallucinates numbers, misreads problems, and reaches wrong answers while sounding careful. Do not trust its outputs. Not evaluated for coherence, factuality, or alignment/safety. For research and curiosity only. Unofficial; not affiliated with Thinking Machines or NVIDIA.

A demonstration that reasoning style can be distilled into a tiny, heavily-pruned MoE — while reasoning ability cannot. Runs on a 16 GB Apple-silicon Mac.

What it is

Built from thinkingmachines/Inkling-Small (a 256-routed-expert MoE) by:

Pruning to 8 of 256 routed experts (~97% of routed params removed), 4-bit MLX.
LoRA-healing back to coherence on FineWeb-Edu → Wikipedia.
Instruction-tuning on OpenHermes-2.5.
Reasoning-distilling on chain-of-thought traces from ianncity/KIMI-K2.5-1000000x and nvidia/Nemotron-Cascade-2-SFT-Data.

The result talks like a careful reasoner. It cannot reliably be one — 8 experts is far too little capacity to restore the base model's knowledge or arithmetic. That gap is the whole point of the demo.

Example (rep-penalty 1.3, `User:/Assistant:` format)

User: A store has 15 apples and sells 8. How many are left?
Assistant: <think>
There is a simple arithmetic problem to find the number of remaining apples.
The store currently holds **15** apples. It plans to sell **8** apples from its inventory.
So we need to calculate: ...

Reads the problem faithfully, sets up the reasoning — then the actual computation falls apart. Representative: fluent reasoning form, unreliable substance.

How to run

GGUF (recommended) — needs the Inkling llama.cpp branch

Stock llama.cpp cannot load Inkling. Build PR #25731 (danielhanchen/llama.cpp, branch add-inkling), then:

# CPU only: Metal offload is buggy in the PR build; -ngl 0 works (~14 tok/s)
llama-cli -m inkling-tiny-reasoning-v1-Q4_K_M.gguf -no-cnv -st -ngl 0 --temp 0 \
  -p $'User: If a train travels 60 mph for 2 hours, how far does it go?\n\nAssistant:'

Files: -Q4_K_M.gguf (~~8 GB, fits 16 GB) and -Q8_0.gguf (~~14 GB).
Use a repetition penalty (~1.3) — greedy loops on <think>. (Opposite of a concise chat model.)

MLX (adapter)

adapter/adapters.safetensors is the reasoning LoRA (rank 16, scale 2). Apply it over the 4-bit MLX base inkling-mlx-k8 (from cebopp1/inkling-tiny-preview) using the bundled inkling_mlx/ runtime + run.py. Requires mlx mlx-lm transformers numpy.

Limitations

Confabulates. Wrong numbers, misread problems, invented facts — stated confidently.
Not factual, not safety-tested, English-only, text-only. No red-teaming or refusal training.
Format-sensitive: best in User:/Assistant:, needs the rep penalty above.

Licenses & attribution

This is a modified derivative work; components carry different licenses. Your use must comply with all:

Base model — thinkingmachines/Inkling-Small: Apache-2.0.
MLX runtime (inkling_mlx/) — from mlx-community/Inkling-Small-mlx: Apache-2.0 (one-line moe.py stop_gradient change for trainability).
Reasoning data — ianncity/KIMI-K2.5-1000000x: Apache-2.0.
Reasoning data — nvidia/Nemotron-Cascade-2-SFT-Data: NVIDIA Open Model License — because this model was trained partly on that data, the NVIDIA Open Model License terms attach to it (hence this repo's license: other).

Unofficial. Not affiliated with, sponsored by, or endorsed by Thinking Machines or NVIDIA.

Downloads last month: 104

MLX

Hardware compatibility

Quantized

GGUF

Model size

14B params

Architecture

inkling

Hardware compatibility

4-bit

8-bit

Model tree for cebopp1/inkling-tiny-reasoning-v1

Base model

thinkingmachines/Inkling-Small

Adapter

(5)

this model

inkling-tiny-reasoning-v1

What it is

Example (rep-penalty 1.3, User:/Assistant: format)

How to run

GGUF (recommended) — needs the Inkling llama.cpp branch

MLX (adapter)

Limitations

Licenses & attribution

Model tree for cebopp1/inkling-tiny-reasoning-v1

Example (rep-penalty 1.3, `User:/Assistant:` format)