Article
Minima leverages Qdrant to achieve 2.78x more agentic RAG tasks on one GPU
This is a joint benchmark of Qdrant retrieval and Minima-optimized inference with Qwen3.6-27B model on one RTX PRO 6000 Blackwell.
Read articleMinima Blog
Minima Blog
Research notes and systems writing on efficient inference, agent infrastructure and the economics of useful intelligence.
Article
53% More Tokens Per GPU: Solving Both Halves of the AI Infrastructure Problem
Minima solved the efficiency problem inside the inference worker: 53% more tokens from Qwen3.6-27B on Blackwell. Rafay Token Factory solved the operability problem around it: a governed, token-metered service.
Read articleBenchmark with us
See what Minima can do for your model and GPUs.
Send us the model, hardware and workload you care about. We will propose a benchmark with explicit quality, throughput, memory and cost gates.
Benchmark your model