moonshine tiny

moonshine tiny · by UsefulSensors

UsefulSensors/moonshine-tiny

UsefulSensors · on speech-pod · vendor build

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 Nov 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.

Languages, proved

Each question was put entirely in its own language and script, and the answer had to be right. A model with no coverage cannot parse the question, so answering in English is a failure here, not a pass. 1 proved of 7 asked — a language absent from the probe set was never asked, and is not a claim either way.

what it produced, measured

speech recognition
produced16stook0.8sspeed21× faster than realtime

measured on Linux, 4 cores, 31 GB · realtime_factor 0.05 (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

Speech inpassed
Whether the model itself accepts audio in a turn — distinct from this gram running a separate transcription engine. Recorded as unmeasured until an engine exposes the path, never as a failure.
signed by this network

What machines here proved

best throughput21× faster than realtime
resident while loaded0.7 GiB · did:epn:002408…e3654f
machines that measured it6
regions it was proved in4
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.

Proven across regions

Measured by

ranked on the provider standings

Every machine that measured it

nothing is averaged — the machine is what you are choosing
did:epn:002408…9e3c79Sundargarh · 769015 · speech-pod · 21 Sept 202612th Gen Intel Core i3-12100 · 15.7 GiB RAM
✓ Speech in · 8.1× faster than realtimeprobe 7E4Wo+1mvo…
✓ Speech in✓ 1 languages
did:epn:002408…a5be46Washington · 20511 · speech-pod · on host · 19 Oct 2026
✓ Speech in · 15× faster than realtimeprobe V3GZGd7OBz…
✓ Speech in✓ 1 languages
did:epn:002408…e61d3bNorth Charleston · 29415 · speech-pod · on host · 26 Oct 2026
✓ Speech in · 13× faster than realtimeprobe rbkEasdUiI…
✓ Speech in✓ 1 languages
did:epn:002408…e3654fNorth Charleston · 29415 · speech-pod · on pod · 26 Oct 2026
✓ Speech in · 14× faster than realtimeprobe UUZd/2awXf…
✓ Speech in✓ 1 languages
did:epn:002408…dae679Singapore · 190464 · speech-pod · on pod · 3 Nov 2026
✓ Speech in · 30× faster than realtimeprobe 3Yu94cnld/…
✓ Speech in✓ 1 languages
did:epn:002408…662a4eNorth Charleston · 29415 · speech-pod · on pod · 5 Nov 2026Intel Xeon @ 2.20GHz · 2 cores · 31.3 GiB RAM
✓ Speech in · 21× faster than realtimeprobe uTfBcTMeWP…
✓ Speech in✓ 1 languages