tinyllama-bnb-4bit is a quantized variant of the TinyLlama model created by Unsloth. It uses 4-bit precision via bitsandbytes to drastically reduce memory requirements while maintaining text generation capabilities. The model is designed for local execution in notebooks, scripts, or inference servers and is popular for experimentation and fine-tuning on limited hardware.
Tinyllama Bnb sits in PulseGate's Foundation models & chat category. It focuses on running lightweight large language models with minimal memory usage on consumer hardware. It is built as an open-source project for developers. Tinyllama Bnb is open source under the Apache-2.0 license. Tinyllama Bnb is available on the web and the command line, and it can be self-hosted.
unsloth builds and maintains Tinyllama Bnb, and the product first shipped in 2023. Development happens publicly on GitHub with 68.6k stars and 1.2k commits in the last 90 days. Key capabilities include Text Generation, 4-bit Quantization, and Efficient Inference.
Latest indexed changes and source events
unsloth/tinyllama-bnb-4bit verified by the PulseGate indexer
