Model reference · open weights

Llama-3.2-QLORA_INT4_EO8

Llama-3.2-QLORA_INT4_EO8 is an open-weight language model from Meta. Llama-3.2-1B-Instruct-QLORA_INT4_EO8 (INT4) weighs 1.6 GB; the smallest configuration that runs it is RTX 3060 12 GB.

For self-hosting, compare this build's requirements below with the GPU you plan to rent.

• Llama-3.2-QLORA_INT4_EO8 is a 1.23B parameter text-generation model developed by Meta, designed for multilingual dialogue, agentic retrieval, and summarization tasks.
• The model supports eight languages, including English, German, French, Italian, Portuguese, Hindi, Spanish, and Thai, and operates with an 8k context length.
• It is distributed under the llama3.2 license and utilizes a 4-bit groupwise quantization scheme for weights and 8-bit dynamic quantization for activations.

Summary of the meta-llama/Llama-3.2-1B-Instruct-QLORA_INT4_EO8 model card, 2026-10-01

Hugging Face ↗GitHub ↗Paper ↗