How to use from
llama.cppInstall from WinGet (Windows)
winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf SakuraLLM/GalTransl-v4-4B-2601:Q5_K_S# Run inference directly in the terminal:
llama-cli -hf SakuraLLM/GalTransl-v4-4B-2601:Q5_K_SUse 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 SakuraLLM/GalTransl-v4-4B-2601:Q5_K_S# Run inference directly in the terminal:
./llama-cli -hf SakuraLLM/GalTransl-v4-4B-2601:Q5_K_SBuild 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 SakuraLLM/GalTransl-v4-4B-2601:Q5_K_S# Run inference directly in the terminal:
./build/bin/llama-cli -hf SakuraLLM/GalTransl-v4-4B-2601:Q5_K_SUse Docker
docker model run hf.co/SakuraLLM/GalTransl-v4-4B-2601:Q5_K_SQuick Links
GalTransl-v4-4B基于Sakura-4B-Qwen3-Base-v2
适合luna翻译器等即时翻译场景，迷你好用
6G显存用GalTransl-v4-4B-2601.gguf（Q6K量化）
4G显存用GalTransl-v4-4B-2601-Q5_K_S.gguf
建议使用Sakura_Launcher_GUI启动，上下文长度至少2048。
prompt格式同GalTransl-7B-v3.7
2026.01.28-2601：更新GalTransl-v4-4B-2601，修正输出格式不稳定的问题，并提升翻译质量。 2025.12.17-2512：初版
- Downloads last month
- 1,897
Hardware compatibility
Log In to add your hardware
5-bit
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Install from brew
# Start a local OpenAI-compatible server with a web UI: llama-server -hf SakuraLLM/GalTransl-v4-4B-2601:Q5_K_S# Run inference directly in the terminal: llama-cli -hf SakuraLLM/GalTransl-v4-4B-2601:Q5_K_S