2beng2/Qwen3.8-27B-OrcaRouter-GSQ-RCO-IQ3_XXS-NInfer
Text Generation • Updated • 1.79k
NInferEZ Models
Windows local inference: github.com/BenGamliel/NInferEZ-Manager. Native NInfer artifacts, provenance, licenses and measured results.
Note IQ3_XXS text artifacts: MTP-only and MTP + DFlash2 variants, with RTX 5090 speed samples.
2beng2/Swift-1.5-Qwen3.8-27B-Uncensored-NVFP4-NInfer
Image-Text-to-Text • Updated • 1.19k • 1Note Swift NVFP4 with Vision, MTP and DFlash2; measured quality and decode speed, separate Swift license.
2beng2/Qwen3.8-27B-Heretic-GSQ-RCO-IQ2_XS-NInfer
Text Generation • UpdatedNote Compact text-only IQ2_XS conversion; no embedded Vision or speculative draft.