Instructions to use sappho192/MiLMMT-46-1B-v0.1-ko-en-ja-pruned-130k-imatrix-Q4_K_M-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use sappho192/MiLMMT-46-1B-v0.1-ko-en-ja-pruned-130k-imatrix-Q4_K_M-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="sappho192/MiLMMT-46-1B-v0.1-ko-en-ja-pruned-130k-imatrix-Q4_K_M-GGUF",
	filename="milmmt-pruned-130k-bf16-imatrix-mix-late16-25-ffngateupq8-Q4_K_M.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use sappho192/MiLMMT-46-1B-v0.1-ko-en-ja-pruned-130k-imatrix-Q4_K_M-GGUF 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 sappho192/MiLMMT-46-1B-v0.1-ko-en-ja-pruned-130k-imatrix-Q4_K_M-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf sappho192/MiLMMT-46-1B-v0.1-ko-en-ja-pruned-130k-imatrix-Q4_K_M-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf sappho192/MiLMMT-46-1B-v0.1-ko-en-ja-pruned-130k-imatrix-Q4_K_M-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf sappho192/MiLMMT-46-1B-v0.1-ko-en-ja-pruned-130k-imatrix-Q4_K_M-GGUF: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 sappho192/MiLMMT-46-1B-v0.1-ko-en-ja-pruned-130k-imatrix-Q4_K_M-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf sappho192/MiLMMT-46-1B-v0.1-ko-en-ja-pruned-130k-imatrix-Q4_K_M-GGUF: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 sappho192/MiLMMT-46-1B-v0.1-ko-en-ja-pruned-130k-imatrix-Q4_K_M-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf sappho192/MiLMMT-46-1B-v0.1-ko-en-ja-pruned-130k-imatrix-Q4_K_M-GGUF:Q4_K_M

Use Docker

docker model run hf.co/sappho192/MiLMMT-46-1B-v0.1-ko-en-ja-pruned-130k-imatrix-Q4_K_M-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use sappho192/MiLMMT-46-1B-v0.1-ko-en-ja-pruned-130k-imatrix-Q4_K_M-GGUF with Ollama:
```
ollama run hf.co/sappho192/MiLMMT-46-1B-v0.1-ko-en-ja-pruned-130k-imatrix-Q4_K_M-GGUF:Q4_K_M
```

Unsloth Studio

How to use sappho192/MiLMMT-46-1B-v0.1-ko-en-ja-pruned-130k-imatrix-Q4_K_M-GGUF 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 sappho192/MiLMMT-46-1B-v0.1-ko-en-ja-pruned-130k-imatrix-Q4_K_M-GGUF 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 sappho192/MiLMMT-46-1B-v0.1-ko-en-ja-pruned-130k-imatrix-Q4_K_M-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for sappho192/MiLMMT-46-1B-v0.1-ko-en-ja-pruned-130k-imatrix-Q4_K_M-GGUF to start chatting

Atomic Chat new
Docker Model Runner
How to use sappho192/MiLMMT-46-1B-v0.1-ko-en-ja-pruned-130k-imatrix-Q4_K_M-GGUF with Docker Model Runner:
```
docker model run hf.co/sappho192/MiLMMT-46-1B-v0.1-ko-en-ja-pruned-130k-imatrix-Q4_K_M-GGUF:Q4_K_M
```

Lemonade

How to use sappho192/MiLMMT-46-1B-v0.1-ko-en-ja-pruned-130k-imatrix-Q4_K_M-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull sappho192/MiLMMT-46-1B-v0.1-ko-en-ja-pruned-130k-imatrix-Q4_K_M-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.MiLMMT-46-1B-v0.1-ko-en-ja-pruned-130k-imatrix-Q4_K_M-GGUF-Q4_K_M

List all available models

lemonade list

Model Description

This repository provides an unofficial GGUF derivative of xiaomi-research/MiLMMT-46-1B-v0.1 for local Korean, English, and Japanese translation.

The model was not fine-tuned. It was produced by retaining a 130k-token ko/en/ja-focused vocabulary, applying importance-matrix calibration, and using a mixed quantization policy: Q4_K_M by default, with Q8_0 retained for ffn_gate and ffn_up tensors in transformer blocks 16–25.

File: milmmt-pruned-130k-bf16-imatrix-mix-late16-25-ffngateupq8-Q4_K_M.gguf
Size: 803,547,328 bytes (766.3 MiB / 0.748 GiB)
SHA-256: 5f781fdc9a685212dba3244b7cf2df39625776066043408f769549195f018b0d
Target languages: Korean, English, Japanese
Intended runtime: llama.cpp-compatible runtimes, including LLamaSharp

Against the local MiLMMT Q8_0 baseline, this model achieved a 0.995182 average chrF++ ratio and a 0.991064 worst-direction ratio on the full FLORES+ dev ko/en/ja evaluation. It also passed an independent 100-row devtest check.

This is the current recommended low-VRAM balanced variant from this experiment. It is not the absolute smallest evaluated GGUF, nor the absolute highest-scoring variant; smaller candidates failed the held-out quality gate, while the Q8_0 baseline is substantially larger.

Use the MiLMMT raw translation prompt format:

Translate this from <source language> to <target language>:
<source language>: <text>
<target language>:

This model is intended for translation, not general chat or reliable use in languages outside Korean, English, and Japanese. It is an independent derivative and is not affiliated with or endorsed by Xiaomi or Google.