Instructions to use MicroFlare/NanoFlare-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use MicroFlare/NanoFlare-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 MicroFlare/NanoFlare-v1:Q2_0
# Run inference directly in the terminal:
llama cli -hf MicroFlare/NanoFlare-v1:Q2_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf MicroFlare/NanoFlare-v1:Q2_0
# Run inference directly in the terminal:
llama cli -hf MicroFlare/NanoFlare-v1:Q2_0

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 MicroFlare/NanoFlare-v1:Q2_0
# Run inference directly in the terminal:
./llama-cli -hf MicroFlare/NanoFlare-v1:Q2_0

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 MicroFlare/NanoFlare-v1:Q2_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf MicroFlare/NanoFlare-v1:Q2_0

Use Docker

docker model run hf.co/MicroFlare/NanoFlare-v1:Q2_0

LM Studio
Jan
Ollama
How to use MicroFlare/NanoFlare-v1 with Ollama:
```
ollama run hf.co/MicroFlare/NanoFlare-v1:Q2_0
```
Unsloth Desktop

How to use MicroFlare/NanoFlare-v1 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf MicroFlare/NanoFlare-v1:Q2_0

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": "MicroFlare/NanoFlare-v1:Q2_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use MicroFlare/NanoFlare-v1 with Docker Model Runner:
```
docker model run hf.co/MicroFlare/NanoFlare-v1:Q2_0
```

Lemonade

How to use MicroFlare/NanoFlare-v1 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull MicroFlare/NanoFlare-v1:Q2_0

Run and chat with the model

lemonade run user.NanoFlare-v1-Q2_0

List all available models

lemonade list

Hermes Agent

How to use MicroFlare/NanoFlare-v1 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf MicroFlare/NanoFlare-v1:Q2_0

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 MicroFlare/NanoFlare-v1:Q2_0

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use MicroFlare/NanoFlare-v1 with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf MicroFlare/NanoFlare-v1:Q2_0

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 "MicroFlare/NanoFlare-v1:Q2_0" \
  --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"

NanoFlare is my newest model, based on the recently released Qwen 3.8 27B. It is designed to run completely* on GPU if you have 8GB of VRAM, otherwise it should be able to run on CPU if you have at least 8GB or more of system memory (this has not been tested).

v1.b is the latest version (recommended)

Revision B brings major improvements to the quality of output, especially in code over what we were seeing from rev.A. It also no longer gets into thinking loops that often anymore.

*If you are running NanoFlare on an 8GB GPU, you will have to offload the kv cache to CPU in most cases. And unfortunately this means it's going to be a little slow. If you are running this model on a card that has 10GB or more you should have all the room you need and see much better performance with the kv cache on GPU.

Relative perplexity scores (all tested with wikitext2, lower is better):

Model	Size	2k ctx PPL	8k ctx PPL
v1 revision b	7469.3 MB	8.2480 ±0.05573	7.9631 ±0.05479
unsloth/IQ2_XXS (UD 3.0)	6929.5 MB	7.5441 +/- 0.04906	8.0013 +/- 0.05689
v1 revision a	7165.9 MB	8.6832 ±0.05605	8.1774 ±0.05276
release candidate 1	7442.6 MB	8.7946 ±0.05764	8.2998 ±0.05454
beta 1	7532.8 MB	8.8221 ±0.05797	8.3352 ±0.05506

The model seems to run best at temperature: 0.95 + top-k: 20 (although it works fine at llama.cpp defaults of 0.8 and 40 too).

Note this model has been hyper-compressed, so it's not perfect. It may flake out on you from time to time, but it is mostly fairly stable. Taking quantization to the extreme levels I'm using comes at a cost. The LLM will sometimes not complete its thought process. If you find yourself in this situation, try the prompt again. It often works correctly on the second try when this happens. It seems to be pretty good at most general tasks, and is good at coding. It has forgotten some facts and figures from its training data through the heavy quantization, so I'd recommend giving it web search access or double checking anything its telling you from recall.

A moderate amount of testing has been performed now, but more scores and such will be posted soon. From subjective, manual testing v1b seems to be far superior to v1a.

Downloads last month: 1,007

GGUF

Model size

27B params

Architecture

qwen35

Hardware compatibility

2-bit

View +1 variant

Inference Providers NEW

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

Model tree for MicroFlare/NanoFlare-v1

Base model

Qwen/Qwen3.8-27B

Quantized

(911)

this model