Unverified50% confidenceBenchmarkExact time
The actual benchmark result of running a 17GB model on an M5 Max is approximately 31 tokens/second.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/20/2026
First Seen
Valid until: 1/18/2027
Sources
Related Entities
Related Claims
UnverifiedThe model's peak decoding speed on the test platform is approximately 274 tokens/second.74% similarUnverifiedAccording to Artificial Analysis testing, Grok 4.6 consumes approximately 38k tokens per task at the MXX High tier, while Grok 4.7 surges to 81k tokens.72% similarUnverifiedAccording to the Chinchilla scaling law, the optimal training data volume for a 30B model is approximately 600B–1T tokens.72% similarUnverified根据Artificial Analysis数据，Fable完成单个任务约用33k token，Opus 5约用37k token71% similarUnverifiedMiniMax M3 每个 token 推理时约激活 23B 参数70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1075811API
curl https://kongchang.com/api/v1/knowledge/claims/1075811MCP
get_claim(id=1075811)