Unverified50% confidenceBenchmarkExact time
Jalapeño peaks at 1500 tokens/second when running the GPT-OSS 120B model, approximately twice that of the next-best solution.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/24/2026
First Seen
Valid until: 12/23/2026
Sources
Related Entities
Related Claims
UnverifiedOpenAI's GPT-OSS 20B achieved a measured speed of over 21 tokens/second, nearly twice that of the dense 12B model.71% similarUnverifiedA 2B model requires approximately 4–10 TFLOPs of computation per inference, taking 10–50 milliseconds on an A100 GPU, while a 70B model requires 140–350 TFLOPs and can take up to several seconds.66% similarUnverifiedThe latest model's context length has reached 128K tokens.64% similarUnverifiedGPT-OSS 120B需要大于80GB显存（如H100 GPU）才能运行64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/945797API
curl https://kongchang.com/api/v1/knowledge/claims/945797MCP
get_claim(id=945797)