Unverified50% confidenceBenchmarkExact time
GPT-OSS-20B BF16 loading was reduced from 545 seconds to 70 seconds (7.8× speedup), and Qwen3.5-397B achieved a 1.93× to 2.3× improvement.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/11/2026
First Seen
Valid until: 12/10/2026
Sources
Related Entities
Related Claims
UnverifiedIn a prefill-only test running gpt-oss-120b on 4× B200s, DWDP4 achieves a 1.92× speedup over DEP4 under the MNT 32K/ISL 32K configuration and a 1.54× throughput improvement at saturation (506K vs. 329K tok/s).70% similarUnverifiedIn benchmark testing, Qwen3 27B achieved a generation speed of approximately 40-something tokens per second on 4 modified 2080 Ti cards without NVLink enabled.70% similarUnverifiedWhen deploying Qwen3 27B with 16 GB of VRAM, if some weights are offloaded to system memory, the speed drops sharply from tens of T/s to single digits.69% similarUnverifiedGPT-OSS 20B推理仅需16G显存，微调仅需24G显存68% similarUnverifiedGPT-4-level models can have a Time to First Token (TTFT) of 500–2000ms, while smaller models such as Llama 3.1 8B can achieve a TTFT as low as 100–300ms.68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/897566API
curl https://kongchang.com/api/v1/knowledge/claims/897566MCP
get_claim(id=897566)