Unverified50% confidenceBenchmarkExact time
Parakeet Redux can run on CPU with a disk footprint of 178 MB, compared to the 1.6 GB of Whisper Large V3 Turbo (Whisper CPP version).
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/6/2026
First Seen
Valid until: 1/4/2027
Sources
Related Entities
Related Claims
UnverifiedParakeet Redux is a ternary-quantized speech-to-text model produced by the Moondream team based on NVIDIA Parakeet 0.6B v3, with the size compressed from approximately 1.2 GB to approximately 178 MB.68% similarUnverifiedWhisper small模型约有244M参数，在消费级CPU上即可流畅运行66% similarUnverifiedIn CPU tests on an M2 MacBook Air, Redux achieved 38× real-time speed while Parakeet CPP achieved only 12×, a roughly 3× lead; however, on the Mac GPU the two are close (43× vs. 38/39×).63% similarUnverifiedWhisper large-v3 从 FP16 量化至 INT8 后显存需求约从10GB降至5GB，使其可在消费级8GB显卡上运行61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/979392API
curl https://kongchang.com/api/v1/knowledge/claims/979392MCP
get_claim(id=979392)