How to use from
llama.cpp
Install from brew
brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf TorpedoSoftware/Gemma-3-1B-Roblox-Luau:
# Run inference directly in the terminal:
llama-cli -hf TorpedoSoftware/Gemma-3-1B-Roblox-Luau:
Install from WinGet (Windows)
winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf TorpedoSoftware/Gemma-3-1B-Roblox-Luau:
# Run inference directly in the terminal:
llama-cli -hf TorpedoSoftware/Gemma-3-1B-Roblox-Luau:
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 TorpedoSoftware/Gemma-3-1B-Roblox-Luau:
# Run inference directly in the terminal:
./llama-cli -hf TorpedoSoftware/Gemma-3-1B-Roblox-Luau:
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 TorpedoSoftware/Gemma-3-1B-Roblox-Luau:
# Run inference directly in the terminal:
./build/bin/llama-cli -hf TorpedoSoftware/Gemma-3-1B-Roblox-Luau:
Use Docker
docker model run hf.co/TorpedoSoftware/Gemma-3-1B-Roblox-Luau:
Quick Links

Gemma-3-1B-Roblox-Luau

A fine tune of google/gemma-3-1b-it using boatbomber/roblox-info-dump and boatbomber/the-luau-stack for Roblox domain knowledge.

This is intended to be used for speculative decoding with boatbomber/Gemma-3-27B-Roblox-Luau. It can be used standalone in memory constrained environments, but is not nearly as capable as the 27B model as it has so few weights that it cannot learn the same level of detail.

Available quants:

Quant Size Notes
Q8_O 1.39GB High resource use, but generally acceptable. Use when accuracy is crucial.
Q5_K_M 1.08GB Recommended. Uses Q6_K for half of the attention.wv and feed_forward.w2 tensors, else Q5_K
Q3_K_M 0.89GB Uses Q4_K for the attention.wv, attention.wo, and feed_forward.w2 tensors, else Q3_K. Quality is noticeably degraded.
Downloads last month
83
Safetensors
Model size
1B params
Tensor type
F32
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for TorpedoSoftware/Gemma-3-1B-Roblox-Luau

Quantized
(438)
this model
Quantizations
1 model

Dataset used to train TorpedoSoftware/Gemma-3-1B-Roblox-Luau