Unverified50% confidencePredictionExact time
The Tesla V100's inference speed for running 8B-class models at FP16 precision is approximately in the range of 20–40 tokens/s.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/12/2026
First Seen
Valid until: 12/11/2026
Sources
Related Entities
Related Claims
UnverifiedThe Tesla V100's FP16 compute performance is approximately 31.4 TFLOPS, and up to 125 TFLOPS with Tensor Cores enabled.76% similarUnverifiedIn prefill speed tests, 4 V100 16G cards did not achieve twice the performance of 2 V100 32G cards.71% similarUnverifiedThrough tensor parallelism, 2×H100 can run a 70B model at FP16 precision smoothly and support relatively high concurrency.71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/911571API
curl https://kongchang.com/api/v1/knowledge/claims/911571MCP
get_claim(id=911571)