Instructions to use mindchain/decider-0.8b-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 mindchain/decider-0.8b-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 mindchain/decider-0.8b-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf mindchain/decider-0.8b-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf mindchain/decider-0.8b-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf mindchain/decider-0.8b-GGUF: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 mindchain/decider-0.8b-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf mindchain/decider-0.8b-GGUF: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 mindchain/decider-0.8b-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf mindchain/decider-0.8b-GGUF:Q4_K_M

Use Docker

docker model run hf.co/mindchain/decider-0.8b-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use mindchain/decider-0.8b-GGUF with Ollama:
```
ollama run hf.co/mindchain/decider-0.8b-GGUF:Q4_K_M
```
Unsloth Desktop

How to use mindchain/decider-0.8b-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf mindchain/decider-0.8b-GGUF:Q4_K_M

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": "mindchain/decider-0.8b-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use mindchain/decider-0.8b-GGUF with Docker Model Runner:
```
docker model run hf.co/mindchain/decider-0.8b-GGUF:Q4_K_M
```

Lemonade

How to use mindchain/decider-0.8b-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull mindchain/decider-0.8b-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.decider-0.8b-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use mindchain/decider-0.8b-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 mindchain/decider-0.8b-GGUF:Q4_K_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 mindchain/decider-0.8b-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use mindchain/decider-0.8b-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf mindchain/decider-0.8b-GGUF:Q4_K_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 "mindchain/decider-0.8b-GGUF:Q4_K_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"

decider-0.8b Q4_K_M GGUF — der kleinste Decider, Android-/Edge-Kandidat

Q4_K_M-Quant von Mapika/decider-0.8b (Qwen3.5-0.8B-Base, Apache-2.0) — der kleinste Kopf der decider-Familie: ~505 MB, läuft auf Telefonen, Nano-PCs und alten GPUs.


Revision	Commit-gepinnt `a0a01d6f8135298f400a8c856b355793012ae971` (Stand 2026-09-25; das Repo hat keine Release-Tags — deshalb Commit statt Tag)
Quant	Q4_K_M, 529.297.440 Bytes, sha256 `aa40eca91f41e475b7c20a10af4247e8ae5b623f386b5c24501971909199496b`
Toolchain	llama.cpp Commit `9575389` + `--no-mtp` + bf16-Zwischenstufe (das getestete JevK5-Rezept)
⚠️ Toolchain-Warnung	llama.cpp master (`e351231`, Sep 2026) baut kaputte `qwen3_5_text`-GGUFs: falsche Metadaten (`block_count` 33, `recurrent_layers[33]`, Phantom-`nextn`) und verschobene Gewichte — Modell lädt, Output ist Müll. Pin euren Commit.
Readout-Temperatur	1.03 (Card-Standard der Familie; anders als decider-4b v2: 1.935!)
Prompt-Format	Upstream-Layout: `Context:\n{state}\n\nQuestion: {q}\nOptions:\n(A) …\n(B) …\nAnswer: (` — Buchstaben-Logits lesen, auf Optionen renormieren (÷ 1.03)

Rolle im JEV-Stack

Tier-0/1-Kandidat für Edge und Android: kalibrierte Wahrscheinlichkeiten in einem Forward-Pass. Gold-Set-Zahlen der großen Geschwister: decider-4b v2 (ECE 0,037 ≈ Teacher 0,033) — dieser 0.8b ist der Nächste in unserer Messpipeline.

Verifikation

Jede Entscheidung wird wie beim 4b gegen den bf16-Original-Readout geprüft, bevor sie in Produktion geht. provenance.json liegt bei (Quelle, Commit, sha256, Toolchain).

Downloads last month: 46

GGUF

Model size

0.8B params

Architecture

qwen35

Hardware compatibility

4-bit

Inference Providers NEW

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

Model tree for mindchain/decider-0.8b-GGUF

Base model

Qwen/Qwen3.5-0.8B-Base

Finetuned

Mapika/decider-0.8b

Quantized

(6)

this model