Unverified50% confidenceFactExact time
The top submitter was RTX 4090 (12 submissions), second was RX 6900XT (11), and RTX 5090 had only 10.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/24/2026
First Seen
Valid until: 1/22/2027
Sources
141 Real-World Benchmarks Revealed: How Fast Can Your GPU Really Run Large Models?
bilibili九物AI生产力10/23/2026
Related Entities
Related Claims
UnverifiedWhen batching 8 requests together, a single RTX PRO 6000 can achieve an aggregate throughput of approximately 220 output tok/s, whereas the old configuration of two RTX 3090s achieved only approximately 19 tok/s.74% similarUnverifiedIn testing, an RTX 5070 running the 2-bit quantized version outputs 94 tokens per second.71% similarVerifiedMainstream RTX 4090 graphics cards have only 24 GB of VRAM, while professional-grade A100/H100 cards offer 80 GB each.68% similarUnverifiedThe author's RTX 2080Ti graphics card has 11G of VRAM, which is still strained for model deployment.68% similarUnverified8 GB of VRAM is the standard configuration for mid-range gaming GPUs such as the RTX 3060 and RTX 4060.66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1092283API
curl https://kongchang.com/api/v1/knowledge/claims/1092283MCP
get_claim(id=1092283)