#speculative-decoding

Wiki 1

• 80 tok/s + 128K Context on 12GB VRAM — Qwen3.6 + MTP janvitos's RTX 4070 Super config — Qwen3.6-35B-A3B MTP UD-Q4_K_XL on 12GB via `-fitt 1536`; thread also documents turboquant+MTP on a GTX 1070