MobileLLM-Pro
1B parameters, 128k context — built by the smart-glasses org
Latest: MobileLLM-Pro 1B base/instruct + int4-cpu and int4-accelerator variants (Oct 2025); technical report arXiv:2511.06719 (Nov 2025)
Meta Reality Labs' 1.08B-parameter on-device foundation model (base + instruct) with 128k context, released October 2025. Interleaves local and global attention at a 3:1 ratio (512-token local windows), cutting prefill latency 1.8x and shrinking KV cache from 117MB to 40MB at 8k context. Ships int4 variants for CPU, Apple Neural Engine, and Qualcomm HTP. FAIR Noncommercial Research License.
Why it matters
Reality Labs' production-oriented on-device foundation model: 128k context with interleaved local and global attention (3:1) that cuts prefill latency 1.8x and shrinks the KV cache from 117MB to 40MB at 8k context, shipped with int4 variants for CPU, Apple Neural Engine and Qualcomm HTP. A concrete blueprint for LLMs on glasses and phones.
Facts
- Beats Gemma 3 1B on MMLU (44.8% vs 29.9%) and crushes both Gemma 3 1B and Llama 3.2 1B on HumanEval coding (59.8% vs 41.5% and 37.8%).
- Notably developed by Reality Labs — the smart-glasses org — not FAIR, hinting at its product destination.
Try it yourself
Model on Hugging Face ↗ Chat demo (Hugging Face Space) ↗ Read the technical report ↗
Lineage
Sources
arXiv ↗Hugging Face · MobileLLM Pro ↗Hugging Face · MobileLLM Pro base int4 cpu ↗Hugging Face · MobileLLM Pro base int4 accele ↗