<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"><channel><title>GPUfit — Intel Arc A750</title><link>https://gpufit.tech/gpu/arc-a750/</link><description>New catalog models scored against Intel Arc A750.</description><item><title>NVIDIA Nemotron 3.5 Bolt E4B on Intel Arc A750: Runs</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 fully on your Intel Arc A750 at UD-Q5_K_XL, 8K context, about 43–59 tok/s. Weights 5.43 GB plus 0.14 GB of KV cache — 5.93 GB of 7.13 GB usable. Up to 64K context still fits. 43–59 tok/s.</description></item><item><title>DeepSeek V4.1 Flash 1017 on Intel Arc A750: 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 Intel Arc A750. The smallest quant UD-IQ1_S is 217.0 GB before KV cache, and usable memory is 7.13 GB.</description></item><item><title>LFM2.5 24B A2B on Intel Arc A750: Expert offload</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>Expert offload on your Intel Arc A750: UD-Q4_K_XL keeps shared weights on the GPU and about 11.5 GB of experts in system RAM. About 12–16 tok/s. Active-parameter speed is approximate. 12–16 tok/s.</description></item></channel></rss>