Skip to content
#

m5-max

Here are 7 public repositories matching this topic...

Language: All
Filter by language
tokspur

Private chat and code on your Mac. Run a 177B model on a 128 GB M5 Max: local Qwen3.8 Flash-Next inference with a 65,536-token default or optional 131,072-token context, Tokspur's own Metal engine with native MTP or DFlash2 drafting, and an OpenAI-compatible API. Apache 2.0.

  • Updated Nov 19, 2026
  • C++

Run Kimi K3.1 Pro and DeepSeek V4.1 Flash 1017 locally with Argodrive DS4: NVIDIA CUDA or Apple silicon Metal, NVMe expert streaming, caches and weight preparation. Setup and measured RTX PRO 6000 / M5 Max results included. Based on antirez/ds4; no separate Argodrive app required.

  • Updated Nov 19, 2026
  • C

Add this topic to your repo

To associate your repository with the m5-max topic, visit your repo's landing page and select "manage topics."

Learn more