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
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 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/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 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
- 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/kernel/bake_raw.py from miutti/intel-mac-local-llm: direct link, hf CLI and curl.
- Browser
- Download file 2.34 kB
-
https://huggingface.co/miutti/intel-mac-local-llm/resolve/main/source/kernel/bake_raw.py
- Command line
-
hf download hf://miutti/intel-mac-local-llm/source/kernel/bake_raw.py
-
curl -L -o bake_raw.py https://huggingface.co/miutti/intel-mac-local-llm/resolve/main/source/kernel/bake_raw.py
2.34 kB
| #!/usr/bin/env python3 | |
| # -*- coding: utf-8 -*- | |
| """ | |
| bake_raw.py -- 次元を落とさずに焼く | |
| 次元圧縮(射影)は、掛け算を減らすためにやっていたが、 | |
| 実測で意味の差が潰れることが分かった。 | |
| そこで圧縮はやめ、int8 に量子化するだけにする。 | |
| ・品質の損失は量子化ぶんだけ(ごくわずか) | |
| ・大きさは 1/2(BF16 → int8) | |
| ・全部をメモリに載せず、必要な行だけ mmap で読む | |
| """ | |
| import os, json, math, time, re, sys | |
| from embed_cards import EmbedCards | |
| HERE = os.path.dirname(os.path.abspath(__file__)) | |
| def bake(tag, tokfile, tok_kind, out, pattern=None, report=4000): | |
| e = EmbedCards(tag=tag, tokfile=tokfile, tok_kind=tok_kind) | |
| inv = {} | |
| for b, i in e.vocab.items(): | |
| try: inv[i] = b.decode("utf-8") | |
| except Exception: pass | |
| targets = [] | |
| for tid, w in inv.items(): | |
| w = w.replace("▁", "") | |
| if len(w) < 2: continue | |
| if pattern and not pattern.search(w): continue | |
| targets.append((tid, w)) | |
| print(f" 対象 {len(targets)} 語 × {e.dim} 次元", flush=True) | |
| idx, seen, t0 = {}, set(), time.time() | |
| with open(out + ".bin", "wb") as f: | |
| for n, (tid, w) in enumerate(targets, 1): | |
| if w in seen: continue | |
| v = e.row(tid) | |
| if not v: continue | |
| nrm = math.sqrt(sum(x * x for x in v)) or 1.0 | |
| f.write(bytes(max(0, min(255, int(round(x / nrm * 127)) + 128)) for x in v)) | |
| idx[w] = len(seen); seen.add(w) | |
| if n % report == 0: | |
| el = time.time() - t0 | |
| print(f" {n}/{len(targets)} ({el:.0f}秒, 残り約{el/n*(len(targets)-n):.0f}秒)", | |
| flush=True) | |
| json.dump({"meta": {"source": tag, "dim": e.dim, "quant": "int8", | |
| "count": len(idx)}, "index": idx}, | |
| open(out, "w", encoding="utf-8"), ensure_ascii=False) | |
| print(f" → {len(idx)}語 索引{os.path.getsize(out)/1e6:.1f}MB " | |
| f"+ 本体{os.path.getsize(out+'.bin')/1e6:.0f}MB ({time.time()-t0:.0f}秒)", flush=True) | |
| if __name__ == "__main__": | |
| JP = re.compile(r"[ぁ-んァ-ヴー一-龥]") | |
| bake("llm-jp-3-13b", "llmjp.tokenizer.json", "unigram", | |
| os.path.join(HERE, "jp_cards.json"), pattern=JP) | |