hanxiao / Qwen3.6-35B-A3B-MTP-L4View on GitHub
Deploy Qwen3.6-35B-A3B (Q4_K_XL) + MTP speculative decoding on a single NVIDIA L4 24GB — GCP g2-standard-8 — via the official llama.cpp Docker image. Decode-optimized to ~91–99 tok/s (min ~91 chat, max ~99 math), lossless (full GPU residency + ECC-off).
☆19Aug 24, 2026Updated last month

Alternatives and similar repositories for Qwen3.6-35B-A3B-MTP-L4

Users that are interested in Qwen3.6-35B-A3B-MTP-L4 are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.

Sorting:

Are these results useful?