/inference/facebook-musicgen-small

facebook/musicgen-small

Measured by 6 nodes on hardware we do not own, and signed by each of them. What machines here actually proved — never what the card claims.

matrix built 12 Sept 2026 · every field verified against the signature of the node that produced it, and re-verifiable by you: each signed figure carries the exact bytes the node signed (signing_payload_b64) and the signature over them, and the ed25519 public key is embedded in node_did. effective_ctx is the context length a node PROVED by recall, never the length a model card advertises

context declarednot declaredwhat the runtime reported. A node attests it was told this; nobody attests it is true.

context proved by recallnot probedthe largest size at which a machine could still find tokens planted across the whole prompt — start, middle and end, all of which had to come back.

Both numbers are needed to state a gap, and one of them is missing.

what it produced, measured

music generation

produced4.0ssample rate32.0 kHztook30sspeed7.5× slower than realtime

measured on Windows, 16 cores, 16 GB · realtime_factor 7.49 (wall ÷ media)

The fastest measurement any machine reported, signed by the machine that took it. Every other machine’s numbers are in the table below — a rate is a fact about a model and a computer, and two machines disagreeing is two hardware classes rather than one of them being wrong.

Capabilities, measured

Generates musicpassed

Whether the model composes audio. Recorded as unmeasured until an engine exposes the path.

signed by this network

What machines here proved

best throughput7.5× slower than realtime

machines that measured it6

regions it was proved in6

Every line traces to a node signature.

from the public record · unsigned

What the runtime says about it

No runtime metadata was attested for this model.The only unsigned block on this page. We attest we read these from the runtime — not that they are true. Nobody signs a model card.