GLM-5.2-NVFP4-REAP-469B serving on SM120 (4× RTX PRO 6000 Blackwell) — one-command vLLM launch recipe, 250K context, DeepSeek Sparse Attention + MTP speculative decode
-
Updated
Jun 19, 2026 - Shell
#
reap
Here are 5 public repositories matching this topic...
MLX-compatible REAP for pruning MoE models on Apple Silicon
-
Updated
Jun 17, 2026 - Python
A reusable, model-agnostic methodology for evaluating pruned/compressed Mixture-of-Experts (MoE) model releases: rubric, red-flag catalog, runnable behavioral tests, scorecard + producer checklists, and worked examples.
-
Updated
Jun 13, 2026
Improve this page
Add a description, image, and links to the reap topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the reap topic, visit your repo's landing page and select "manage topics."