<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"><channel><title>GPUfit — GeForce RTX 3060 12GB</title><link>https://gpufit.tech/gpu/rtx-3060-12gb</link><description>New catalog models scored against GeForce RTX 3060 12GB.</description><item><title>bottlecapai ThinkingCap gemma 4 26B A4B it on GeForce RTX 3060 12GB: Tight fit</title><link>https://gpufit.tech/models/bottlecapai-thinkingcap-gemma-4-26b-a4b-it</link><guid>https://gpufit.tech/models/bottlecapai-thinkingcap-gemma-4-26b-a4b-it</guid><pubDate>Fri, 23 Oct 2026 21:26:38 GMT</pubDate><description>Tight fit fully on your GeForce RTX 3060 12GB at IQ2_S, 8K context, about 54–74 tok/s. Weights 9.60 GB plus 0.51 GB of KV cache — 10.5 GB of 10.9 GB usable. 54–74 tok/s.</description></item><item><title>NVIDIA Nemotron 3.5 Bolt E4B on GeForce RTX 3060 12GB: 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 GeForce RTX 3060 12GB at UD-Q8_K_XL, 8K context, about 22–30 tok/s. Weights 7.63 GB plus 0.14 GB of KV cache — 8.15 GB of 10.9 GB usable. Up to 128K context still fits. 22–30 tok/s.</description></item><item><title>DeepSeek V4.1 Flash 1017 on GeForce RTX 3060 12GB: 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 GeForce RTX 3060 12GB. The smallest quant UD-IQ1_S is 217.0 GB before KV cache, and usable memory is 10.9 GB.</description></item><item><title>LFM2.5 24B A2B on GeForce RTX 3060 12GB: 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 on your GeForce RTX 3060 12GB at UD-IQ3_XXS, 8K context, about 140–190 tok/s. Weights 8.34 GB plus 0.63 GB of KV cache — 9.35 GB of 10.9 GB usable. Up to 16K context still fits. 140–190 tok/s.</description></item></channel></rss>