Text Generation
GGUF
Japanese
English
llama.cpp
Mixture of Experts
expert-pruning
intel-mac
cpu
local-agent
imatrix
conversational
Instructions to use miutti/intel-mac-local-llm with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use miutti/intel-mac-local-llm 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 miutti/intel-mac-local-llm:UD-Q2_K_XL # Run inference directly in the terminal: llama cli -hf miutti/intel-mac-local-llm:UD-Q2_K_XL
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf miutti/intel-mac-local-llm:UD-Q2_K_XL # Run inference directly in the terminal: llama cli -hf miutti/intel-mac-local-llm:UD-Q2_K_XL
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 miutti/intel-mac-local-llm:UD-Q2_K_XL # Run inference directly in the terminal: ./build/bin/llama cli -hf miutti/intel-mac-local-llm:UD-Q2_K_XL
Use Docker
docker model run hf.co/miutti/intel-mac-local-llm:UD-Q2_K_XL
- Llama new
- LM Studio
- Jan
- vLLM
How to use miutti/intel-mac-local-llm with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "miutti/intel-mac-local-llm" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "miutti/intel-mac-local-llm", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/miutti/intel-mac-local-llm:UD-Q2_K_XL
- Ollama
How to use miutti/intel-mac-local-llm with Ollama:
ollama run hf.co/miutti/intel-mac-local-llm:UD-Q2_K_XL
- Unsloth Desktop
- Pi
How to use miutti/intel-mac-local-llm with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf miutti/intel-mac-local-llm:UD-Q2_K_XL
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": "miutti/intel-mac-local-llm:UD-Q2_K_XL" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use miutti/intel-mac-local-llm with Docker Model Runner:
docker model run hf.co/miutti/intel-mac-local-llm:UD-Q2_K_XL
- Lemonade
How to use miutti/intel-mac-local-llm with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull miutti/intel-mac-local-llm:UD-Q2_K_XL
Run and chat with the model
lemonade run user.intel-mac-local-llm-UD-Q2_K_XL
List all available models
lemonade list
- Hermes Agent
How to use miutti/intel-mac-local-llm with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf miutti/intel-mac-local-llm:UD-Q2_K_XL
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 miutti/intel-mac-local-llm:UD-Q2_K_XL
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use miutti/intel-mac-local-llm with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf miutti/intel-mac-local-llm:UD-Q2_K_XL
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 "miutti/intel-mac-local-llm:UD-Q2_K_XL" \ --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"
Download source/lib/rotate.py from miutti/intel-mac-local-llm: direct link, hf CLI and curl.
- Browser
- Download file 2.42 kB
-
https://huggingface.co/miutti/intel-mac-local-llm/resolve/main/source/lib/rotate.py
- Command line
-
hf download hf://miutti/intel-mac-local-llm/source/lib/rotate.py
-
curl -L -o rotate.py https://huggingface.co/miutti/intel-mac-local-llm/resolve/main/source/lib/rotate.py
2.42 kB
| """アダマール回転(インコヒーレンス処理)。 | |
| 重み行列は少数の巨大な値と大量の小さい値で出来ていて、これが量子化に最悪。 | |
| 直交行列で回転すると値が均されて「全部そこそこの大きさ」になり、 | |
| 同じビット数でも表現しやすくなる。 | |
| 肝は **回転行列を保存しなくていい** こと。アダマール行列は構造で決まり、 | |
| 符号反転はシード1個で再現できるので、オーバーヘッドは実質ゼロ。 | |
| 推論時は入力 x 側も同じ回転をかける(O(n log n)で安い)。 | |
| """ | |
| import numpy as np | |
| def fwht(a): | |
| """高速ウォルシュ・アダマール変換(最終軸に対して、正規化なし)。""" | |
| a = a.copy() | |
| n = a.shape[-1] | |
| assert n & (n - 1) == 0, "長さは2のべき乗が必要" | |
| h = 1 | |
| while h < n: | |
| a = a.reshape(*a.shape[:-1], n // (2 * h), 2, h) | |
| x = a[..., 0, :].copy() | |
| y = a[..., 1, :].copy() | |
| a[..., 0, :] = x + y | |
| a[..., 1, :] = x - y | |
| a = a.reshape(*a.shape[:-3], n) | |
| h *= 2 | |
| return a | |
| def signs(n, seed): | |
| rng = np.random.default_rng(seed) | |
| return rng.choice(np.array([-1.0, 1.0], np.float32), size=n) | |
| def rotate_rows(A, d, inverse=False): | |
| """A の最終軸に Q = H·diag(d)/√n を掛ける。inverse=True で Qᵀ。""" | |
| n = A.shape[-1] | |
| s = 1.0 / np.sqrt(n) | |
| # ★ 2026-09-07 訂正: ここの説明が逆だった。実測で確かめた事実は: | |
| # inverse=False → A @ Qᵀ | |
| # inverse=True → A @ Q (Q = H·diag(d)/√n) | |
| # 上の docstring は逆に書いてあった。**直したのは説明であって計算ではない。** | |
| # 往復(False→True)で元に戻ることは確認済みなので、 | |
| # これまでの実験結果は1ビットも変わらない。 | |
| if not inverse: | |
| return fwht(A * d) * s # A Q^T 相当(Hは対称) | |
| return fwht(A) * d * s | |
| def make(n, seed=0): | |
| """(重み用の回転関数, 活性化用の回転関数) を返す。両者は必ず打ち消し合う。""" | |
| d = signs(n, seed) | |
| def rot_W(W): # W' = W Q | |
| return rotate_rows(W, d, inverse=False) | |
| def rot_x(X): # x' = Qᵀ x (X は (n, sample)) | |
| return rotate_rows(X.T, d, inverse=False).T | |
| return rot_W, rot_x, d | |