Instructions to use ModernoTech/Nova-Mini with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use ModernoTech/Nova-Mini 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 ModernoTech/Nova-Mini:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf ModernoTech/Nova-Mini:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf ModernoTech/Nova-Mini:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf ModernoTech/Nova-Mini:Q4_K_M

Build from source code

git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-app
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama serve -hf ModernoTech/Nova-Mini:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama cli -hf ModernoTech/Nova-Mini:Q4_K_M

Use Docker

docker model run hf.co/ModernoTech/Nova-Mini:Q4_K_M

Llama new
LM Studio
Jan
Ollama
How to use ModernoTech/Nova-Mini with Ollama:
```
ollama run hf.co/ModernoTech/Nova-Mini:Q4_K_M
```
Unsloth Desktop

How to use ModernoTech/Nova-Mini with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ModernoTech/Nova-Mini: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": "ModernoTech/Nova-Mini:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use ModernoTech/Nova-Mini with Docker Model Runner:
```
docker model run hf.co/ModernoTech/Nova-Mini:Q4_K_M
```

Lemonade

How to use ModernoTech/Nova-Mini with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ModernoTech/Nova-Mini:Q4_K_M

Run and chat with the model

lemonade run user.Nova-Mini-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use ModernoTech/Nova-Mini with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ModernoTech/Nova-Mini: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 ModernoTech/Nova-Mini:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use ModernoTech/Nova-Mini with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ModernoTech/Nova-Mini: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 "ModernoTech/Nova-Mini: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"

ModernoTech commited on 6 days ago

Commit

becba17

verified ·

1 Parent(s): 75bba09

branding: apply unified Moderno Tech / Nova visual identity

Browse files

Files changed (1) hide show

README.md +46 -21

README.md CHANGED Viewed

@@ -2,7 +2,6 @@
 language:
 - en
 - es
-- zh
 pretty_name: Nova Mini 1.0 — Moderno Tech
 model_name: Nova Mini 1.0
 model_creator: Moderno Tech
@@ -13,44 +12,70 @@ tags:
 - text-generation
 - gguf
 - conversational
-- qwen3
 license: apache-2.0
 base_model: Qwen/Qwen3-0.6B
 inference: false
 ---
 # Nova Mini 1.0
-**Nova Mini 1.0** es un modelo publicado por **Moderno Tech** dentro de la familia **Nova Edge**.
-La identidad principal del producto es **Nova Mini 1.0**, creado por Moderno Tech bajo la familia Nova.
-Los pesos conservan la arquitectura y cuantización originales. Moderno Tech no afirma haberlos entrenado desde cero.
-## Identidad comercial
-- Product name: `Nova Mini 1.0`
 - Commercial version: `1.0`
-- Organization: `Moderno Tech`
-- Family: `Nova Edge`
-- Base model: `Qwen/Qwen3-0.6B`
-- Published artifact: `Nova-Mini-1.0-Q4_K_M.gguf`
-- Original artifact filename: `Qwen3-0.6B-Q4_K_M.gguf`
-## Provenance
-- Original repository: `Qwen/Qwen3-0.6B-GGUF` y `ModernoTech/nova-models`
-- Quantization: Q4_K_M
 - Expected bytes: 484220288
 - SHA-256: `03a9f2b5eaa26e8a801012cf5c2eb75f2997da0725ce99bc03622d4bae583fdd`
-## License
-Redistribution y use are subject to Apache License 2.0 and the original Qwen licensing terms.
-Moderno Tech did not change weights, architecture, tokenizer, prompts or inference parameters.
-## Consistency note
-The branded filename preserves the exact original weight integrity, bytes and SHA-256.
-It is not a conversion and not a recalculation of weights.

 language:
 - en
 - es
 pretty_name: Nova Mini 1.0 — Moderno Tech
 model_name: Nova Mini 1.0
 model_creator: Moderno Tech
 - text-generation
 - gguf
 - conversational
 license: apache-2.0
 base_model: Qwen/Qwen3-0.6B
 inference: false
 ---
+<div align="center">
+  <img alt="Moderno Tech" src="images/moderno-tech-logo.png" width="120"/>
+  <img alt="Nova Mini" src="images/nova-logo.png" width="160"/>
+  <br/>
+  <h1>Nova Mini 1.0</h1>
+  <p><strong>Moderno Tech · Nova Edge</strong></p>
+  <p>Compact intelligence. Moderno Technology.</p>
+</div>
 # Nova Mini 1.0
+**Nova Mini 1.0** es un producto de **Moderno Tech**, publicado como parte de la familia **Nova Edge**.
+La identidad principal del producto es **Nova Mini 1.0**, creado por Moderno Tech. La procedencia técnica se conserva en una sección secundaria.
+La identidad visual y editorial de Moderno Tech / Nova se aplica a este repositorio. Los pesos iniciales corresponden al artefacto original verificado y se publican como la primera generación de distribución del producto.
+## Product identity
+- Product name: **Nova Mini 1.0**
+- Organization: **Moderno Tech**
+- Family: **Nova Edge**
 - Commercial version: `1.0`
+- Base parameters: 0.6B (600M)
+- Format: GGUF
+- Quantization: Q4_K_M
+- Product artifact: `Nova-Mini-1.0-Q4_K_M.gguf`
+## Intended use
+Nova Mini ofrece una opción compacta para inferencia local y conversacional en dispositivos con recursos limitados.
+No se afirma aquí que Moderno Tech haya entrenado estos pesos desde cero en esta primera publicación. Este repositorio establece la identidad, distribución, documentación y estructura del producto para una evolución futura.
+## Specifications
+- Published artifact: `Nova-Mini-1.0-Q4_K_M.gguf`
+- Original artifact filename: `Qwen3-0.6B-Q4_K_M.gguf`
 - Expected bytes: 484220288
 - SHA-256: `03a9f2b5eaa26e8a801012cf5c2eb75f2997da0725ce99bc03622d4bae583fdd`
+- Quantization: Q4_K_M`
+## Usage
+Suggested parameters when running the original artifact are documented in the original repository.
+## Technical provenance and licensing
+- Base model: `Qwen/Qwen3-0.6B`
+- Original repository: `Qwen3-0.6B-Q4_K_M.gguf` (documented above)
+- Licensed under `Apache License 2.0`.
+- Original authors and license terms must remain visible and respected.
+- Moderno Tech redistributes and documents the verified artifact without changing weights, architecture, tokenizer, prompts or inference parameters.
+## Versioning
+- `1.0 — Initial Nova-branded distribution
+- Later versions will retain the same Nova Mini identity while evolving weights, fine-tuning and distillation.
+## About Moderno Tech / Nova
+Moderno Tech develops the Nova family as a coherent AI product line with custom branding, documentation and a progressive technical roadmap toward Nova-native models.