MobileLLM-Flash
Architecture search with real phone latency in the loop
Latest: MobileLLM-Flash 350M/650M/1.4B (paper Mar 16, 2026; ACL Industry Track 2026)
Latest MobileLLM generation (350M/650M/1.4B) designed via hardware-in-the-loop architecture search under real mobile latency constraints, with attention skipping for long-context acceleration up to 8k. Paper (Mar 2026) accepted to ACL 2026 Industry Track. Weights had not been publicly released as of Sept 2026.
Why it matters
Designs the model around the phone rather than the benchmark: hardware-in-the-loop architecture search under real mobile latency constraints, plus attention skipping to accelerate contexts up to 8k. Accepted to the ACL 2026 Industry Track; as of September 2026 the weights had not been released, so only the paper is available.
Facts
- Up to 1.8x faster prefill and 1.6x faster decode on mobile CPUs vs comparable-quality models.
- Represents a methodology shift for the family: instead of hand-designed architecture rules (MobileLLM's deep-and-thin), the architecture itself is searched with actual phone latency in the loop.
- Only community trackers list a weights release; Meta's own HF collection did not include it.