Unverified50% confidenceBenchmarkExact time
With a 5070 12 GB GPU paired with 64 GB of memory and MTP enabled, generation speed can exceed 50 tokens/s, with official tests reaching 60–95 tokens/s.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/5/2026
First Seen
Valid until: 1/3/2027
Sources
Related Entities
Related Claims
Unverified使用SGLang同时开启Prefix Cache和MTP后，token生成速度提升到约40-50 tokens/s75% similarUnverified同等参数的Dense模型在没有MTP的情况下，生成速度通常只有40-50 tokens/s75% similarUnverifiedIn prefill speed tests, Halo achieved approximately 650 tokens/s while Spark achieved approximately 2000 tokens/s, with Spark being nearly three times faster.75% similarUnverifiedIn actual benchmark threads for llama.cpp, the 2021 M1 Max achieved a decode write speed of 61 tokens/s, higher than the 2024 M4 Pro's 51 tokens/s.71% similarUnverifiedUnder this configuration, the 35B model achieves a measured single-user peak speed of approximately 80 tokens/second, with concurrent throughput exceeding 500 tokens/second.69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/978797API
curl https://kongchang.com/api/v1/knowledge/claims/978797MCP
get_claim(id=978797)