GraySoft
Projects Models Compare Cloud benchmarks FAQ Download guIDE →

localweights author hub

Qwen3.6 35B A3B MTP IMAT IQ4 XS Q8nextn GGUF 35B MoE Qwen3.6 A3B trunk 3B active + embedded NextN MTP head, quantized for single GPU inference. Trunk: IQ4 XS imatrix calibrated MTP head: Q8 0 NextN, kv only nextn=true File size: ~18.3 GB Min VRAM: ~21 GB at 32K ctx with KV Q8/Q8…

Models
2
Downloads
784

Run models locally with guIDE

Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.

Download guIDE → · Browse 524k+ models · Compare models