Unverified50% confidenceFactExact time
Whisper model sizes downloadable within the InsertKit app: Tiny about 75 MB, Base about 140 MB, Small about 460 MB, Medium about 1.5 GB, Large v3 about 3 GB.
1
Sources
50%
Confidence
Long-term
Relevance
10/18/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedWhisper原始FP32版本的Tiny模型约150MB，经INT8量化后可压缩至约40MB，在树莓派4B上可实现实时转写79% 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79% similarUnverifiedWhisper ASR (large-v3) averaged approximately 7.7 GB of VRAM over 7 days and peaked at approximately 10.3 GB.74% similarVerifiedAfter 4-bit quantization, Llama 3.3 70B has a model size of approximately 40 GB and can run on a Mac Studio with 64 GB of memory or a single professional GPU with 48 GB of VRAM.70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1058628API
curl https://kongchang.com/api/v1/knowledge/claims/1058628MCP
get_claim(id=1058628)