Unverified50% confidenceBenchmarkExact time
When 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.
1
Sources
50%
Confidence
Long-term
Relevance
10/12/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedA ~25 GB Q3 model running entirely within the RTX 4090's VRAM (bandwidth ~1 TB/s) theoretically achieves ~40 tokens per second, whereas running it in DDR5 memory (~80 GB/s) drops throughput to 1–3 tokens per second.76% similarUnverifiedThe TTS voice model's weights are approximately 4.5 GB, with measured usage at 4.7–4.8 GB, because TTS is stateless between requests and has no long context or queue buffers.76% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1002810API
curl https://kongchang.com/api/v1/knowledge/claims/1002810MCP
get_claim(id=1002810)