Instructions to use clemsail/micro-kiki-v3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use clemsail/micro-kiki-v3 with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="clemsail/micro-kiki-v3",
	filename="micro-kiki-v3-Q4_K_M.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use clemsail/micro-kiki-v3 with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf clemsail/micro-kiki-v3:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf clemsail/micro-kiki-v3:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf clemsail/micro-kiki-v3:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf clemsail/micro-kiki-v3: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 clemsail/micro-kiki-v3:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf clemsail/micro-kiki-v3: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 clemsail/micro-kiki-v3:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf clemsail/micro-kiki-v3:Q4_K_M

Use Docker

docker model run hf.co/clemsail/micro-kiki-v3:Q4_K_M

LM Studio
Jan

vLLM

How to use clemsail/micro-kiki-v3 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "clemsail/micro-kiki-v3"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "clemsail/micro-kiki-v3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/clemsail/micro-kiki-v3:Q4_K_M

Ollama
How to use clemsail/micro-kiki-v3 with Ollama:
```
ollama run hf.co/clemsail/micro-kiki-v3:Q4_K_M
```

Unsloth Studio new

How to use clemsail/micro-kiki-v3 with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for clemsail/micro-kiki-v3 to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for clemsail/micro-kiki-v3 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for clemsail/micro-kiki-v3 to start chatting

Pi new

How to use clemsail/micro-kiki-v3 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf clemsail/micro-kiki-v3:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "clemsail/micro-kiki-v3:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use clemsail/micro-kiki-v3 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf clemsail/micro-kiki-v3: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 clemsail/micro-kiki-v3:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use clemsail/micro-kiki-v3 with Docker Model Runner:
```
docker model run hf.co/clemsail/micro-kiki-v3:Q4_K_M
```

Lemonade

How to use clemsail/micro-kiki-v3 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull clemsail/micro-kiki-v3:Q4_K_M

Run and chat with the model

lemonade run user.micro-kiki-v3-Q4_K_M

List all available models

lemonade list

v3 release — what's new, what's next, feedback welcome

by clemsail - opened Apr 18

Discussion

clemsail

Owner Apr 18

Hi everyone — micro-kiki-v3 just dropped (17/04). Opening this thread to share context and collect feedback.

What this is

A cognitive LLM stack specialized in embedded engineering, not a flat fine-tune:

Router → top-4 selection among 35 domain-specific LoRA stacks
Base — Qwen3.5-35B-A3B (MoE 256 experts, 3B active/token), rank-16 LoRAs on q/k/v/o, top-2 routing per stack
Null-space projection between stacks to reduce catastrophic forgetting
Negotiator (CAMP + Catfish) when stacks disagree
Anti-bias layer (KnowBias + RBD) before output
Aeon memory (Atlas graph + Trace log) for cross-session persistence

Context 262K tokens, GGUF, Apache 2.0, French + English interleaved.

Companion release — training toolkit is also public

We released the training toolkit one day earlier: L-electron-Rare/KIKI-Mac_tunner — an MLX fine-tuning toolkit (Mac Studio) for distilling Claude Opus reasoning into Mistral Large 123B. The full pipeline is open, not just the artifact.

Dataset

clemsail/micro-kiki-v3-dataset — 489K instruction-following examples across 35 domains:

50,116 real Claude CLI sessions captured on our 5-node P2P mesh during actual embedded consulting work (GrosMac M5, Tower, CILS, KXKM-AI RTX 4090, VM bootstrap)
364K from 19 filtered open-source HF datasets (CodeFeedback, French-Alpaca, Electronics StackExchange, stm32-hal-dataset, etc.)
Opus teacher distillation for chat-fr and reasoning
32 original curated seed sets per domain

What I'd love from you

Benchmarks against base Qwen3.5 / GPT-4 / Claude on embedded-specific tasks — I only have internal eval. A reproducible public benchmark is on the v4 roadmap but community runs would help.
Edge cases where the router picks the wrong stack — especially useful for improving the classifier in v4.
Memory/inference regressions on your hardware (Q4_K_M works cleanly on Apple Silicon 32GB+ and RTX 4090; other configs untested).
Domains we missed — the 35 categories are pragmatic not exhaustive, happy to add in v4.

Ecosystem overview: github.com/L-electron-Rare — 13 public repos spanning the FineFab platform (hardware, firmware, CAD, ML).

Issues, forks, negative findings all welcome. Apache 2.0 means fork it, break it, improve it.

— Clément / L'Électron Rare

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment