Expired50% confidenceBenchmarkExact time
LFM2.5-24B-A2B achieves throughput of over 21,000 tokens/second on a single NVIDIA B300 private cloud accelerator.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
10/14/2026
First Seen
This claim has expired. It is kept for the record and no longer describes the current state.
Valid until: 10/28/2026(expired)
Sources
Related Entities
Related Claims
VerifiedA single NVIDIA A100 card has 80GB HBM2e memory and 312 TFLOPS of FP16 computing power73% similarVerifiedEach SM on the NVIDIA A100 has 65,536 32-bit registers.73% similarVerifiedThe NVIDIA H20's peak BF16 compute is approximately 296 TFLOPS, significantly reduced compared to the H100's 989 TFLOPS, but it retains 141 GB HBM3 memory and 4.0 TB/s memory bandwidth.70% similarUnverifiedThe NVIDIA A100 has a memory bandwidth of 2 TB/s; loading a 280 GB FP32 model takes approximately 140 ms, meaning weight loading alone limits generation to a maximum of approximately 7 tokens per second.70% similarUnverifiedNVIDIA released an NVFP4 quantized model of Qwen3 235B on Hugging Face, compressing the model from approximately 470 GB of VRAM in BF16 to approximately 156 GB, enabling it to run on a single-node cluster of 8 H100 GPUs.70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1029989API
curl https://kongchang.com/api/v1/knowledge/claims/1029989MCP
get_claim(id=1029989)