verifier.org

MobileLLM

meta's research line for sub-billion-parameter on-device models

#research#sub-1b

MobileLLM is listed here for coverage of the category. the entry is ours, not the vendor's: we have not tested it, there is no score, and no pricing is quoted because we have not read it off their own page on a date we can cite.

if you work on MobileLLM, claim the listing through /submit and replace this with your own description.

the description above is supplied by the vendor and is not something we have tested. pricing is as they state it.

pricing
not stated
website
github.com

more small on-device llms

TinyLlama

1.1b model trained on 3t tokens, a common baseline for tiny deployments

#baseline#1b

H2O Danube

h2o.ai's small models released for edge and offline use

#edge

Gemma 4 (E2B / E4B / 12B)

we checked thisfree (apache 2.0)

text, images and audio on a phone, under an apache licence google took three generations to arrive at.

#anything-that-needs-to-s#on-hardware-you-already-

Qwen3.5-4B-Instruct

we checked thisfree (apache 2.0)

262k of context in about three gigabytes, apache 2.0, and two generations newer than the qwen everyone links to.

#long-document-work-on-a-#where-the-context-window