Unverified50% confidenceFactExact time
The Whistle speech transcription model released by Cactus Compute is only 16.9MB (about 17MB) in file size.
1
Sources
50%
Confidence
Long-term
Relevance
10/21/2026
First Seen
Sources
17MB Speech Transcription Model Whistle: A New Option for On-Device Deployment
youtubeNeuralNine10/21/2026
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71% similarUnverifiedWhisper 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.68% similarUnverifiedWhen running Whisper ASR, a TTS voice model, and nomic-embed-text simultaneously on an RTX 3090 with 24 GB of VRAM, the three resident models occupied 17.8 GB (72%) of VRAM, peaked at 23.4 GB over the course of a week, and never spilled over into system memory.65% similarUnverifiedQwen 3.8's 27-billion-parameter model is approximately 15.3 GB after 4-bit quantization, but actual memory usage can surge to over 17 GB after a conversation of several thousand characters, meaning 16 GB of VRAM is insufficient and 24 GB is needed for comfortable use.65% similarUnverifiedEmbedding Gemma 2 has 740 million parameters, consisting of a 270M text encoder, a 170M vision encoder, and a 300M audio encoder, with runtime dynamic memory of approximately 191MB to 567MB; the 270M version requires a minimum of 0.5GB memory to run, and the full multimodal version can run locally with 1GB of memory.65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1082568API
curl https://kongchang.com/api/v1/knowledge/claims/1082568MCP
get_claim(id=1082568)