Expired50% confidenceFactExact time
The NVIDIA 5090 released in 2025 increased VRAM to 32GB and introduced FP4 inference support.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/2/2026
First Seen
Valid until: 9/30/2026(expired)
Sources
Related Claims
UnverifiedNVIDIA B200于2024年发布，FP16算力达到4.5 PFLOPS级别70% similarUnverifiedVideo generation models in their original FP16 format may require more than 20GB of VRAM, which can be compressed to under 5GB after Q4 quantization.66% similarUnverifiedNVFP4量化需要50系列NVIDIA显卡才能使用66% similarUnverifiedWhen deploying the Qwen3 27B NVFP4 model on a 5090 (32 GB VRAM), vLLM can support a context length of approximately 70K.65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/47575API
curl https://kongchang.com/api/v1/knowledge/claims/47575MCP
get_claim(id=47575)