https://blog.geoffcorey.com/tags/qwen3.6/ Recent content in Qwen3.6 on Geoff Corey's Blog Hugo en Wed, 22 Apr 2026 00:00:00 +0000 https://blog.geoffcorey.com/posts/missile-command-qwen3.6-claude/ Wed, 22 Apr 2026 00:00:00 +0000 https://blog.geoffcorey.com/posts/missile-command-qwen3.6-claude/ <p>I wanted to try pointing Claude CLI to a local LLM and see how well it would work. My machine is running linux EndevourOS has the following specs:</p> <div class="highlight"><pre tabindex="0" style="color:#f8f8f2;background-color:#272822;-moz-tab-size:4;-o-tab-size:4;tab-size:4;-webkit-text-size-adjust:none;"><code class="language-text" data-lang="text"><span style="display:flex;"><span>Monitor 3840x2160 in 27&#34;, 60 Hz [External] </span></span><span style="display:flex;"><span>Monitor 3840x2160 in 32&#34;, 60 Hz [External] </span></span><span style="display:flex;"><span>CPU 12th Gen Intel(R) Core(TM) i9-12900KF @5.20 GHz 52.0°C </span></span><span style="display:flex;"><span>GPU AMD Radeon RX 9070 - 48.0°C [Discrete] </span></span><span style="display:flex;"><span>G Driver amdgpu </span></span><span style="display:flex;"><span>Vulkan 1.4.335 - radv [Mesa 26.0.5-arch1.1] </span></span><span style="display:flex;"><span>Motherboard PRIME Z690M-PLUS D4 (Rev 1.xx) </span></span><span style="display:flex;"><span>Bios 3811 (38.11) </span></span><span style="display:flex;"><span>RAM ●●●● 23.94 GiB / 62.60 GiB (38%) </span></span></code></pre></div><p>I use llama-cpp to run the model locally. During this experiment I kept hitting the context limit. I bumped it pretty high but then again, I have plenty of memory.</p>