metaai·lightalo unofficial · independent
Universe / On-Device & Silicon / MobileLLM-Pro
On-Device & Silicon · 2025

MobileLLM-Pro

1B parameters, 128k context — built by the smart-glasses org

open source 1.08B params
❝ 4 citations⤓ 42 downloads/moread 2026-09-03

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

Try it yourself

Lineage

Descends fromMobileLLM

See the whole family tree →

Sources

More in On-Device & Silicon

MobileLLM-R1 / R1.5GPU superclusters: 350K H100s → Prometheus & HyperionMobileLLM-FlashQuantized Llama 3.2Meta LLM CompilerMTIA

Read the On-Device & Silicon story on the sky →

✦ Open on the map Explore On-Device & Silicon Quiz me