REAM: Merging Improves Pruning of Experts in LLMs
Paper • 2604.04356 • Published • 8
🤝 Open to Collab
Matt
Basher17
AI & ML interests
Uploading high-quality MLX quantizations of models I use.
Recent Activity
new activity about 3 hours ago
Aleph-Alpha/Kolibri-1:Can someone produce a oQ4e quant? reacted to gianlucamazza's post with 🔥 about 3 hours ago
GGUF models from xllama's catalogue, my independent research project for local LLM inference on an Xbox Series S. Each note gives the measured figures or test status, with model, quant and setup. For example, LFM2.5-350M (QAD Q4_0, Dev Mode, llama.cpp CPU) decodes at 101.6 tok/s. Source for every number: xllama's model matrix. Not affiliated with Microsoft.
https://huggingface.co/collections/gianlucamazza/xllama-models-measured-on-xbox-series-s-6aca0b32275cbe99dbf02d89 liked a model 1 day ago
scaryrawr/MiniCPM-V-4.7-35B-A3B-oQ4eOrganizations
