Unverified50% confidenceBenchmarkExact time
Whisper ASR (large-v3) averaged approximately 7.7 GB of VRAM over 7 days and peaked at approximately 10.3 GB.
1
Sources
50%
Confidence
Long-term
Relevance
10/12/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedWhisper 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77% 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.68% similarUnverified本地运行 Whisper large 版本至少需要8GB 显存的 GPU65% similarUnverifiedDeepSeek-V3 has a total of 685B parameters, and even after Q4 quantization its size still exceeds 400GB.63% similarUnverifiedDify 1.8.0 对应的 Docker 镜像总体积约 5~6GB，10GB 以内足够，下载速度相比之前版本明显提升63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1002811API
curl https://kongchang.com/api/v1/knowledge/claims/1002811MCP
get_claim(id=1002811)