MiniMax AI M2.7 achieves record inference speeds with SambaNovaAI

MiniMax AI has announced a significant speed improvement for its M2.7 model, achieving new world records for inference speed. In partnership with SambaNovaAI, the models reached 850 tokens per second on short-context workloads and over 450 tokens per second on long-context workloads. This performance was benchmarked by Artificial Analysis and was achieved by pairing SambaNovaAI's H200s for prefill with SN50 RDUs for decoding. AI

IMPACT Sets new inference speed benchmarks, potentially improving efficiency for AI applications.

RANK_REASON The item details a new benchmark result for an AI model's inference speed. [lever_c_demoted from research: ic=1 ai=1.0]

Read on X — MiniMax AI →

• Artificial Analysis
• H200s
• MiniMax AI
• MiniMax M2.7
• SambaNovaAI
• SN50 RDUs

• model release
• infra

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →