xero0000 author hub
Qwen3.6 35B A3B — vram13: an all VRAM ultra quant 12.98 GB, imatrix A 35B MoE that fits entirely in 18 GB of VRAM and decodes at 122–159 t/s on a pair of mid range gaming GPUs RTX 3060 Ti 8 GB + RTX 3080 10 GB , with quality within ~1 % perplexity of Q8 0. Most sub 24 GB rigs ru…
Models
4
Downloads
0
Run models locally with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.