Instructions to use stanthegorilla/S1-mini-Q8_0-Q6_K-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use stanthegorilla/S1-mini-Q8_0-Q6_K-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 stanthegorilla/S1-mini-Q8_0-Q6_K-GGUF:Q6_K
# Run inference directly in the terminal:
llama cli -hf stanthegorilla/S1-mini-Q8_0-Q6_K-GGUF:Q6_K

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf stanthegorilla/S1-mini-Q8_0-Q6_K-GGUF:Q6_K
# Run inference directly in the terminal:
llama cli -hf stanthegorilla/S1-mini-Q8_0-Q6_K-GGUF: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 stanthegorilla/S1-mini-Q8_0-Q6_K-GGUF:Q6_K
# Run inference directly in the terminal:
./llama-cli -hf stanthegorilla/S1-mini-Q8_0-Q6_K-GGUF: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 stanthegorilla/S1-mini-Q8_0-Q6_K-GGUF:Q6_K
# Run inference directly in the terminal:
./build/bin/llama-cli -hf stanthegorilla/S1-mini-Q8_0-Q6_K-GGUF:Q6_K

Use Docker

docker model run hf.co/stanthegorilla/S1-mini-Q8_0-Q6_K-GGUF:Q6_K

LM Studio
Jan
Ollama
How to use stanthegorilla/S1-mini-Q8_0-Q6_K-GGUF with Ollama:
```
ollama run hf.co/stanthegorilla/S1-mini-Q8_0-Q6_K-GGUF:Q6_K
```
Unsloth Desktop

How to use stanthegorilla/S1-mini-Q8_0-Q6_K-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf stanthegorilla/S1-mini-Q8_0-Q6_K-GGUF:Q6_K

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "stanthegorilla/S1-mini-Q8_0-Q6_K-GGUF:Q6_K"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use stanthegorilla/S1-mini-Q8_0-Q6_K-GGUF with Docker Model Runner:
```
docker model run hf.co/stanthegorilla/S1-mini-Q8_0-Q6_K-GGUF:Q6_K
```

Lemonade

How to use stanthegorilla/S1-mini-Q8_0-Q6_K-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull stanthegorilla/S1-mini-Q8_0-Q6_K-GGUF:Q6_K

Run and chat with the model

lemonade run user.S1-mini-Q8_0-Q6_K-GGUF-Q6_K

List all available models

lemonade list

Hermes Agent

How to use stanthegorilla/S1-mini-Q8_0-Q6_K-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 stanthegorilla/S1-mini-Q8_0-Q6_K-GGUF: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 stanthegorilla/S1-mini-Q8_0-Q6_K-GGUF:Q6_K

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use stanthegorilla/S1-mini-Q8_0-Q6_K-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf stanthegorilla/S1-mini-Q8_0-Q6_K-GGUF: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 "stanthegorilla/S1-mini-Q8_0-Q6_K-GGUF: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"

S1-mini · GGUF

Two GGUF builds of S1-mini by Superwhisper, the speech-transcript normalizer, made for Lathe, a local push-to-talk dictation app for Windows. Superwhisper publishes F16 and Q4_K_M at superwhisper/s1-mini-GGUF; these fill the gap between them.

File	Size	Output identical to F16	Decode, RX 6600 XT
`s1-mini-q8_0.gguf`	805 MB	94% / 95% (synthetic / real dictations)	246 tokens/s
`s1-mini-q6_k-mixed.gguf`	636 MB	86% / 92%	272 tokens/s
F16 (upstream)	1,509 MB	reference	150 tokens/s
Q4_K_M (upstream)	484 MB	76% / 77%	325 tokens/s

Q4_K_M was observed dropping whole clauses from dictations; neither build here did on 202 test inputs. Where Q6_K mixed differs from F16 it is nearly always punctuation, or a filler removed that F16 kept.

Q8_0: llama-quantize on the upstream F16, no importance matrix (Q8_0 does not use one).

Q6_K mixed: Q6_K with an importance matrix calibrated on 266 real dictations in the model's own prompt format, then per tensor: the output head and the six blocks a sensitivity sweep found most fragile (0, 11, 16–19) at Q8_0; attn_v, attn_output, ffn_up, ffn_down at Q6_K; attn_q, attn_k, ffn_gate at Q5_K; the token embedding at Q4_K.

Full comparison of fourteen builds, including the recipes that did not beat plain Q8_0, in Lathe's docs.

Prompt format

S1-mini has a fixed contract: the system prompt below verbatim, then a control line and the raw transcript, thinking disabled, greedy decoding.

<|im_start|>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.<|im_end|>
<|im_start|>user
[Styling: semi-formal] [Structure: prose] [Context: general]
okay so can you send me the the file from yesterday not the older one thanks<|im_end|>
<|im_start|>assistant
<think>

</think>

Styling: casual, semi-casual, semi-formal, formal. Structure: prose, lists. Context: general, email.

License

Apache 2.0, inherited from S1-mini and from Qwen3-0.6B (Alibaba Cloud), with Superwhisper's additional term: any use or distribution of this model must continue to identify it as "S1-mini" by "Superwhisper". See LICENSE and NOTICE, copied unchanged from the upstream repo.

Downloads last month: 162

GGUF

Model size

0.8B params

Architecture

qwen3

Hardware compatibility

6-bit

8-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for stanthegorilla/S1-mini-Q8_0-Q6_K-GGUF

Base model

Qwen/Qwen3-0.6B-Base

Finetuned

Qwen/Qwen3-0.6B

Finetuned

superwhisper/s1-mini

Quantized

(12)

this model