Unverified50% confidenceFactExact time
When reading gpu_log.csv on a T4, one typically sees the same pattern: clocks.sm holds steady at 1590 in the first minute, then gradually drops to 1200–1350 between minutes 3 and 5 and stabilizes.
1
Sources
50%
Confidence
Long-term
Relevance
10/17/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedDeveloper Primitive reported: 91.2 tokens/s with speculative decoding off, reaching 142.6 tokens/s after enabling 3 speculative tokens, approximately a 56% speedup under the same configuration.60% similarVerifiedModern CPU L1 cache access latency is approximately 0.5 nanoseconds, L2 approximately 4 nanoseconds, and a single main memory access requires 60–100 nanoseconds.59% similarUnverifiedWhen running Qwen3-Next-Flash (Autoround W4A16 quantization), the prefill speed was approximately 1.3k tokens/s, and the generation speed reached 70 tokens/s (code) / 60 tokens/s (prose), with support for 128k+ long context.57% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1050236API
curl https://kongchang.com/api/v1/knowledge/claims/1050236MCP
get_claim(id=1050236)