gpu-performance

Tag

Cards List
#gpu-performance

@populartourist: Having worked consistently with Qwen3.6 27B NVFP4 on repos - it's clear that this quant is not reliable, at least for c…

X AI KOLs Timeline · yesterday Cached

The user reports that the Qwen3.6 27B NVFP4 quantization is unreliable for coding, with inconsistent quality despite high throughput, and suggests that Q4_K_M may be more consistent.

0 favorites 0 likes
#gpu-performance

@TeksEdge: Unsloth released the fastest Qwen3.6-27B MTP GGUF I've tested. Time to upgrade. Compared to the previous GGUF, Q4/Q6 XL…

X AI KOLs Timeline · 2026-05-12

Unsloth has released an optimized GGUF version of the Qwen3.6-27B MTP model, achieving significantly faster inference speeds (up to 114 tok/s on an RTX 5090) compared to previous quantizations.

0 favorites 0 likes
← Back to home

Submit Feedback