Unverified50% confidenceFactExact time
Compute used a single Lambda GH200 (64 ARM cores plus an H100 96GB), running 15,360 games in parallel, with throughput of 1.2 to 1.9 million samples per second.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
11/2/2026
First Seen
Valid until: 1/31/2027
Sources
Related Entities
Related Claims
UnverifiedAccording to hands-on information shared by a Bilibili creator, on a hardware platform with 128G unified memory, 873G bandwidth, and 2070 TOPS of compute, a Qwen 30B-class model achieved over 100 TPS in a single stream on coding tasks.68% similarUnverifiedFreeToken在8GB显存笔记本上可运行约35B参数模型,游戏级桌面显卡可运行284B参数模型,工作站单卡可运行753B参数模型67% similarUnverified7900XT搭载Navi 31核心,拥有96个计算单元、20GB GDDR6显存,理论FP16算力超过80 TFLOPS67% similarUnverifiedOn a single-GPU machine with 96 GB of VRAM and 188 GB of system memory, Qwen3.8 Flash Next was successfully run by offloading the embedding table and Ngram to system memory.67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1125552API
curl https://kongchang.com/api/v1/knowledge/claims/1125552MCP
get_claim(id=1125552)