models · thinkingmachines

Inkling Small

Inkling Small — catalogued from third-party evaluation data; no weights held by Sovereign Frontier.

Compare 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.
Methodhf-published-sha256

What is recorded

Publisherthinkingmachines
OriginUnited States
LicenceApache-2.0
Parameters265,956,439,090 (266B)
Context window1,048,576 tokens
Modalitytext+image+audio->text
Native precisionBF16
Downloads reported upstream73,353

Reported scores

GPQA Diamond89.5
Humanity's Last Exam33.3

Reported by a third party and recorded here, not re-run by us. Source: artificialanalysis.ai/api/v2.

Measured on real hardware

None of these runs are ours. Each figure is the reporter’s, linked to their own evidence, under their own trust label. The number shown is single-stream decode — one user, concurrency 1 — because aggregate throughput across many users is a different quantity and reads as far faster than anyone will see.

Reported to local-ai-registry

HardwareEngineBuild measuredDecode, 1 streamLabelReported by
RTX PRO 6000 Blackwell ×2 devicessglangModelOpt NVFP4115 tok/s @ 50candidateppickle1989
GeForce RTX 3090 ×6 devicesllama.cppIQ4_XS47.4 tok/s @ 262,144candidatelocalmaxxing
NVIDIA DGX Spark GB10 ×2 devicesvllmModelOpt NVFP432.3 tok/s @ 563candidate0xsero

From local-ai-registry (MIT), commit 124959d: 4 runs across 3 machines, 0 validated — model revision and runtime pinned, launch accepted — and 4 candidate, their label for useful evidence without a reproducible-launch promise.

Elsewhere in the registry

Registry record as of 2026-08-15. 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.