Unverified50% confidenceBenchmarkExact time
MiniMax officially only supported SM100 professional servers at first; after the uploader added SM120 support for it, speed rose from 45 tokens/s to 51.6 tokens/s.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
10/25/2026
First Seen
Valid until: 11/8/2026
Sources
Related Entities
Related Claims
UnverifiedEarly users report that MiniMax M3.1 Flash decodes at 90–110 tokens/second, but MiniMax has not yet published official speed data.69% similarUnverifiedA UP host running MiniCPM 2B with an RTX 4080S (16GB VRAM) + 64GB RAM configuration achieved an inference speed of approximately 110 tokens/second in real-world testing67% similarUnverifiedRunning Gemma 4 26B on an M3 Max, MLX is 65.0 tokens/s and LLAMA.cpp is 63.9 tokens/s, essentially a tie between the two.66% similarUnverifiedIn terms of prompt processing speed, the RTX 4090 achieves approximately 3,000 tokens/s and the M5 Max approximately 800 tokens/s, giving NVIDIA a clear advantage in long-document and codebase input scenarios.66% similarUnverifiedMiniMax M3.1 Flash's thinking tokens count toward the max_tokens limit, so reusing the 4K or 8K caps from the M2.x era may cause truncation with finish_reason: "length"; MiniMax recommends raising max_tokens to 131,072, with an upper limit of 524,288.65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1095841API
curl https://kongchang.com/api/v1/knowledge/claims/1095841MCP
get_claim(id=1095841)