Instructions to use librepowerai/TriLM-3.9B-TQ2_0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use librepowerai/TriLM-3.9B-TQ2_0 with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="librepowerai/TriLM-3.9B-TQ2_0",
	filename="TriLM-3.9B-TQ2_0-be.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 librepowerai/TriLM-3.9B-TQ2_0 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 librepowerai/TriLM-3.9B-TQ2_0:TQ2_0
# Run inference directly in the terminal:
llama cli -hf librepowerai/TriLM-3.9B-TQ2_0:TQ2_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf librepowerai/TriLM-3.9B-TQ2_0:TQ2_0
# Run inference directly in the terminal:
llama cli -hf librepowerai/TriLM-3.9B-TQ2_0:TQ2_0

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 librepowerai/TriLM-3.9B-TQ2_0:TQ2_0
# Run inference directly in the terminal:
./llama-cli -hf librepowerai/TriLM-3.9B-TQ2_0:TQ2_0

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 librepowerai/TriLM-3.9B-TQ2_0:TQ2_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf librepowerai/TriLM-3.9B-TQ2_0:TQ2_0

Use Docker

docker model run hf.co/librepowerai/TriLM-3.9B-TQ2_0:TQ2_0

LM Studio
Jan
Ollama
How to use librepowerai/TriLM-3.9B-TQ2_0 with Ollama:
```
ollama run hf.co/librepowerai/TriLM-3.9B-TQ2_0:TQ2_0
```

Unsloth Studio

How to use librepowerai/TriLM-3.9B-TQ2_0 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 librepowerai/TriLM-3.9B-TQ2_0 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 librepowerai/TriLM-3.9B-TQ2_0 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for librepowerai/TriLM-3.9B-TQ2_0 to start chatting

Atomic Chat new
Docker Model Runner
How to use librepowerai/TriLM-3.9B-TQ2_0 with Docker Model Runner:
```
docker model run hf.co/librepowerai/TriLM-3.9B-TQ2_0:TQ2_0
```

Lemonade

How to use librepowerai/TriLM-3.9B-TQ2_0 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull librepowerai/TriLM-3.9B-TQ2_0:TQ2_0

Run and chat with the model

lemonade run user.TriLM-3.9B-TQ2_0-TQ2_0

List all available models

lemonade list

TriLM 3.9B — TQ2_0 GGUF for IBM Power

TriLM 3.9B (Spectra Suite, ternary {-1, 0, +1} weights) quantized to TQ2_0 (2.06 bits per weight) for fast CPU inference with llama.cpp — optimized for IBM POWER9 and later with the LibrePower VSX ternary kernels.

File: TriLM-3.9B-TQ2_0.gguf (1.46 GiB, 3.99 B parameters)
Quantization: TQ2_0 — exact ternary, no quality loss vs the original ternary weights
No GPU required.

Run it on IBM Power (ppc64le)

curl -fsSL https://linux.librepower.org/install.sh | sudo sh
sudo apt install librepower-llama

lp-llama-completion -m TriLM-3.9B-TQ2_0.gguf -p "Once upon a time" -n 64 -t 48

Works with any recent llama.cpp on any architecture; the LibrePower build adds VSX acceleration on Power (4.3x prompt / 2.4x generation vs the generic path).

AIX / big-endian

TriLM-3.9B-TQ2_0-be.gguf is the big-endian variant for IBM AIX (dnf install llama-aix from aix.librepower.org):

lp-llama-completion -m TriLM-3.9B-TQ2_0-be.gguf -p "Once upon a time" -n 64 -t 16

Performance (IBM POWER9, Ubuntu 22.04, llama-bench)

Test	Threads	Tokens/s
Prompt processing (pp64)	96	121.2
Generation (tg64)	48	29.5
Generation (tg64)	24	22.3

Note: this is a base model (no instruction tuning) — use completion-style prompts, not chat.

Credits

Model: Spectra Suite (Apache 2.0)
TQ2_0 quantization & Power packaging: LibrePower

Downloads last month: 4,748

GGUF

Model size

4B params

Architecture

llama

Hardware compatibility

2-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for librepowerai/TriLM-3.9B-TQ2_0

Base model

SpectraSuite/TriLM_3.9B_Unpacked

Quantized

(3)

this model