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 9 public repositories matching this topic...
MLX-compatible REAP for pruning MoE models on Apple Silicon
-
Updated
Sep 6, 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
Deploy the GLM-5.2-469B model on four RTX PRO 6000 Blackwell GPUs using a turnkey vLLM Docker configuration to enable high-speed sparse attention and inference.
android open-source benchmark ocr smartthings smartapp moe glm zwave gles2 reap vllm chatglm-6b long-horizon rtx-pro-6000
-
Updated
Sep 17, 2026 - Shell
How I fit 35B-parameter MoE models into 16 GB of consumer VRAM: REAP expert pruning + NVFP4 quantization on an RTX 5070 Ti (SM120), served on vLLM, with measured evals.
moe quantization reap mixture-of-experts blackwell vllm llm-inference consumer-gpu nvfp4 expert-pruning
-
Updated
Sep 9, 2026
REAP pruning + NVFP4 quantization of Ornith-1.5-35B-A3B for 16GB VRAM
-
Updated
Sep 14, 2026 - Python
Add this topic to your repo
To associate your repository with the reap topic, visit your repo's landing page and select "manage topics."