Tailored inference engines, by GPU and model.

News

• dflash2-int8kvqwen3.8-27b@NVFP4updated 23 Oct 2026
• mtp3-host-expertsqwen3.8-flash-next@NVFP4updated 23 Oct 2026
• mtp7-device-confidenceqwen3.8-27b@NVFP4added 23 Oct 2026

Trending

By Hugging Face downloads of the checkpoint, last 30 days.

• mtp7-device-confidenceunsloth/Qwen3.8-27B-NVFP41.5M downloads/month · 522 likes
• mtp3-host-expertsnvidia/Qwen3.8-Flash-Next-NVFP4376.5k downloads/month · 387 likes
• dflash2-int8kvQUASAR-QAT/Qwen3.8-27B-QUASAR-NVFP494.5k downloads/month · 161 likes