<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"><channel><title>GPUfit — AMD Ryzen AI Max+ 395</title><link>https://gpufit.tech/cpu/ryzen-ai-max-395/</link><description>New catalog models scored against AMD Ryzen AI Max+ 395.</description><item><title>NVIDIA Nemotron 3.5 Bolt E4B on AMD Ryzen AI Max+ 395: Runs great</title><link>https://gpufit.tech/models/nvidia-nemotron-3-5-bolt-e4b/</link><guid>https://gpufit.tech/models/nvidia-nemotron-3-5-bolt-e4b/</guid><pubDate>Fri, 23 Oct 2026 09:47:55 GMT</pubDate><description>Runs great fully in unified memory on your AMD Ryzen AI Max+ 395 at BF16, 8K context, about 8.9–12 tok/s. Weights 14.0 GB plus 0.14 GB of KV cache — 14.6 GB of 48.0 GB usable. Up to 128K context still fits. 8.9–12 tok/s.</description></item><item><title>DeepSeek V4.1 Flash 1017 on AMD Ryzen AI Max+ 395: Won't fit</title><link>https://gpufit.tech/models/deepseek-v4-1-flash-1017/</link><guid>https://gpufit.tech/models/deepseek-v4-1-flash-1017/</guid><pubDate>Sat, 17 Oct 2026 20:36:06 GMT</pubDate><description>Won't fit on AMD Ryzen AI Max+ 395. The smallest quant UD-IQ1_S is 217.0 GB before KV cache, and usable memory is 48.0 GB.</description></item><item><title>LFM2.5 24B A2B on AMD Ryzen AI Max+ 395: Tight fit</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>Tight fit fully in unified memory on your AMD Ryzen AI Max+ 395 at BF16, 8K context, about 7.0–9.5 tok/s. Weights 44.7 GB plus 0.63 GB of KV cache — 46.0 GB of 48.0 GB usable. Up to 16K context still fits. 7.0–9.5 tok/s.</description></item></channel></rss>