Avatar
Mia @MiaAI_lab · 15h
You want more? I have more ⚡ Qwen3.8-Flash-Next on a single NVIDIA DGX Spark just got even better - Prefill at 8k is now 24.7% faster - Single-stream prose: ~47 tok/s, up from 44 - Fixed a speculative drafting bug that could cause up to a 24% drop in decode performance in Show more
39
29
416
20K
Layout & Display Mode
Media & Profile Picture
Avatar Thumb
Profile Avatar
Tap or Drag & Drop image
🖼️
Attached Tweet Media
Attach photo or graphic
Profile & Tweet Text
Engagement Metrics & Background Theme