NInfer: 271 tok/s (543 with speculative) for Qwen3.6-35B-A3B on one RTX 5090 #1 Post by opwizardx » Thu, Jul 23, 2026, 11:49 AM UTC NInfer: 271 tok/s (543 with speculative) for Qwen3.6-35B-A3B on one RTX 5090github.com
Re: NInfer: 271 tok/s (543 with speculative) for Qwen3.6-35B-A3B on one RTX 5090 #2 Post by opwizardx » Thu, Jul 23, 2026, 1:00 PM UTC [dead]