Termux-LlamaCpp

디바이스 리소스를 활용한 Android Termux ARM64 전용 GGUF LLM 런타임, 모델 매니저 및 OpenAI 호환 REST/SSE 서버
Production-Grade GGUF LLM Runtime Utilizing Device Resources, Model Manager & OpenAI Server for Android ARM64

Architecture & Overview

검증된 Android Bionic ARM64 네이티브 바이너리와 필수 공유 라이브러리, 디바이스 리소스 최적화 연동을 통해 제로 컴파일 로컬 실행과 안정적인 OpenAI 호환 REST/SSE 스트리밍 서버를 제공합니다.

Ships verified Android ARM64 native binaries with bundled shared libraries and device resource optimization, enabling instant zero-compilation local inference and a robust OpenAI-compatible REST/SSE server.

Installation & Quickstart

Python (PyPI)

pip install termux-llamacpp

from termux_llamacpp import LlamaRuntime, RuntimeConfig

# 1. Initialize Runtime with Vulkan GPU Acceleration
config = RuntimeConfig(
    model_path="models/Llama-3.2-1B-Instruct-Q4_K_M.gguf",
    device="auto",
    threads=4,
    context_size=2048
)
runtime = LlamaRuntime(config)

# 2. Synchronous or Streaming Text Generation
output = runtime.generate("한국의 사계절 중 가을의 매력에 대해 설명해줘.", max_tokens=256)
print(output.text)
print(f"Speed: {output.metrics.eval_tokens_per_sec:.2f} t/s (Prompt: {output.metrics.prompt_tokens_per_sec:.2f} t/s)")

Node.js / TypeScript (npm)

npm install termux-llamacpp

import { LlamaRuntime } from "termux-llamacpp";

// 1. Initialize ESM Runtime
const runtime = new LlamaRuntime({
  modelPath: "models/Llama-3.2-1B-Instruct-Q4_K_M.gguf",
  device: "auto",
  threads: 4
});

// 2. Generate Completion
const result = await runtime.generate({
  prompt: "Explain the architectural philosophy of edge computing.",
  maxTokens: 256
});
console.log("Response:", result.text);
console.log(`Generation Speed: ${result.metrics.evalTokensPerSec} t/s`);

Official Documentation & Benchmarks

License

termux llama.cpp gguf android llm arm64 openai-server on-device-ai edge-ai mobile-ai vulkan vulkan-compute gpu-acceleration local-ai snapdragon adreno arm-mali exynos zero-compilation supply-chain-security ed25519-verification server-sent-events streaming-inference chat-completions rest-api function-calling tool-calling vision-llm multimodal-ai mmproj qwen2.5 llama3 gemma2 deepseek mistral phi3 huggingface model-manager reverse-proxy daemon-supervisor termux-aichain termux-tts termux-stt termux-diffusion ameva-runtime quantization-q4 bionic-libc mmap-inference autonomous-agents ai-orchestrator

Metadata

Release files for termux-llamacpp 1.3.10

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for termux-llamacpp 1.3.10
File	Size	Uploaded
termux_llamacpp-1.3.10.tar.gz	178.4 kB	Sep 28, 2026	Details

Built distribution (wheel)

Table of built distributions (wheels) for termux-llamacpp 1.3.10
File	Interpreter	ABI	Platform	Reset
termux_llamacpp-1.3.10-py3-none-any.whl 71.0 kB Sep 28, 2026	Python 3	none	any	Details

Total release size: 249.4 kB

Release files / termux_llamacpp-1.3.10.tar.gz

Download URL	termux_llamacpp-1.3.10.tar.gz
Size	178.4 kB
Tags	Source
SHA-256 checksum How to use checksums	`839afdbb9bbd7ed1cb191f5b8cc5c0bac030af1afd6cea177b82cdccbe80ebef`
BLAKE2b-256 checksum How to use checksums	`88d3c58f3b599f1f235fb7c6e3af3ba9d45094b531f469bb42ad54f12934b007`
Upload date	Sep 28, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/7.0.0 CPython/3.11.16`

Release files / termux_llamacpp-1.3.10-py3-none-any.whl

Download URL	termux_llamacpp-1.3.10-py3-none-any.whl
Size	71.0 kB
Tags	Python 3
SHA-256 checksum How to use checksums	`0a116130a412800220687e3b22710981ba55392f4e4d60380e1bca3a26edc981`
BLAKE2b-256 checksum How to use checksums	`ee53a255825592fbb1ed871de48f20f97cb018eb5916cc80f5f1f1f99cb972e4`
Upload date	Sep 28, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/7.0.0 CPython/3.11.16`