Oct 18, 2026NVFP4 vs FP8 vs GGUF on a 16 GB Ada GPU: NVFP4 decodes 2.3x faster and ties BF16 on GSM8KEfrain Garay
Oct 14, 2026Kandinsky 6.0 on a 16 GB GPU: the official recipe runs out of memory, and only the 29B model passed my Spanish testEfrain Garay
Oct 12, 2026Qwen-Image 2.1 on 16 GB of VRAM, quantized to NF4: a real benchmark against FLUXEfrain Garay
