<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"><channel><title>GPUfit — new models</title><link>https://gpufit.tech/new</link><description>Newly tracked open models.</description><item><title>LFM2.5 24B A2B</title><link>https://gpufit.tech/models/lfm2-5-24b-a2b</link><guid>https://gpufit.tech/models/lfm2-5-24b-a2b</guid><pubDate>Tue, 13 Oct 2026 14:19:48 GMT</pubDate><description>24.0B lfm2moe. LFM2.5 24B A2B is a 24.0B mixture-of-experts lfm2moe model from unsloth, with about 2.0B parameters active per token. Configured context length is 131,072 tokens. License: other. Quant sizes are the GGUF file bytes published on Hugging Face when a file exists. Catalog 2026-10-17.</description></item></channel></rss>