architectures · tiiuae

Falcon

Decoder-only transformer using multi-query attention — one shared key/value head across all query heads — which shrinks the KV cache substantially at long context and was the design's headline inference property. Parallel attention and feed-forward blocks; rotary position embeddings. Trained on the RefinedWeb corpus, published alongside the models. Declared as model_type `falcon`.

Verify

What this registry has checked

Quarantine. We hold the publisher’s own published hash for these weights and have recorded it against this entry. We have not downloaded and hashed the weights ourselves, so the hash is the publisher’s claim, not our measurement.
Re-check this yourself → Source → Full record →

What is recorded

Publishertiiuae
OriginUnited Arab Emirates
LicenceApache-2.0

Elsewhere in the registry

All architectures → Browse with filters → What will run on my hardware? →

Registry record as of 2026-08-14. Identity, licence and parameter count are properties of a release and do not move; tier can, and the verify link above re-checks it against the live registry rather than this page.