Instructions to use iniyanai/s1-mini-6bit-mlx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use iniyanai/s1-mini-6bit-mlx 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("iniyanai/s1-mini-6bit-mlx")

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

How to use iniyanai/s1-mini-6bit-mlx with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "iniyanai/s1-mini-6bit-mlx"

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": "iniyanai/s1-mini-6bit-mlx"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

MLX LM

How to use iniyanai/s1-mini-6bit-mlx with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "iniyanai/s1-mini-6bit-mlx"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "iniyanai/s1-mini-6bit-mlx"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "iniyanai/s1-mini-6bit-mlx",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Hermes Agent

How to use iniyanai/s1-mini-6bit-mlx 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 "iniyanai/s1-mini-6bit-mlx"

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 iniyanai/s1-mini-6bit-mlx

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use iniyanai/s1-mini-6bit-mlx with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "iniyanai/s1-mini-6bit-mlx"

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 "iniyanai/s1-mini-6bit-mlx" \
  --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"

S1-mini by Superwhisper (6-bit MLX)

A 6-bit MLX conversion of S1-mini by Superwhisper, used as the on-device cleanup model in Quill, a free, open-source dictation app for macOS.

S1-mini is made by Superwhisper. This repo only changes the weight format so it runs through Apple's MLX on Apple Silicon. All credit for the model goes to Superwhisper; see the original model card for training details, evaluations, and the full usage guide.

Conversion

mlx_lm convert --hf-path superwhisper/s1-mini --mlx-path s1-mini-6bit -q --q-bits 6

About 6.5 bits per weight, 473 MB. 6-bit was chosen over 4-bit because 4-bit dropped commas and sentence-final periods in testing, while 6-bit matched the original BF16 output.

Usage

S1-mini needs its exact system prompt and a control line, greedy decoding, and thinking disabled:

from mlx_lm import load, generate
from mlx_lm.sample_utils import make_sampler

model, tok = load("iniyanai/s1-mini-6bit-mlx")
SYSTEM = "You are a text normalizer for speech-to-text transcripts. The input begins with a control line specifying the styling, structure, and context settings; clean the transcript to match those settings and output only the cleaned text."
user = "[Styling: semi-formal] [Structure: prose] [Context: general]\nso um send the report by uh friday"
prompt = tok.apply_chat_template(
    [{"role": "system", "content": SYSTEM}, {"role": "user", "content": user}],
    add_generation_prompt=True, enable_thinking=False, tokenize=False,
)
print(generate(model, tok, prompt, max_tokens=128, sampler=make_sampler(temp=0.0)))
# So send the report by Friday.

License

Same license as the original: Apache 2.0 with an additional naming term (see LICENSE and NOTICE). Any use or distribution must identify the model as "S1-mini" by "Superwhisper", with that exact capitalization.