https://freesoftware.blog/ 2026-09-19T03:55:53+00:00 https://freesoftware.blog/hello-world/ 2026-09-19T03:55:50+00:00 https://freesoftware.blog/wp-content/uploads/2026/09/hello-world-featured-scaled.jpg https://freesoftware.blog/a-developer-guide-to-paged-attention-and-kv-cache-optimization/ 2026-09-19T03:54:37+00:00 https://freesoftware.blog/wp-content/uploads/2026/09/featured-image-0.jpg https://freesoftware.blog/benchmarking-consumer-gpus-for-high-throughput-quantized-inference/ 2026-09-18T03:54:42+00:00 https://freesoftware.blog/wp-content/uploads/2026/09/featured-image-1.jpg https://freesoftware.blog/ditching-the-cloud-running-70b-parameter-models-on-bare-metal/ 2026-09-17T03:54:49+00:00 https://freesoftware.blog/wp-content/uploads/2026/09/featured-image-2.jpg https://freesoftware.blog/understanding-awq-vs-gptq-selecting-the-best-quantization-scheme/ 2026-09-16T03:54:54+00:00 https://freesoftware.blog/wp-content/uploads/2026/09/featured-image-3.jpg https://freesoftware.blog/optimizing-tensorrt-llm-and-vllm-for-local-deployment/ 2026-09-15T03:54:59+00:00 https://freesoftware.blog/wp-content/uploads/2026/09/featured-image-4.jpg https://freesoftware.blog/zero-to-inference-custom-local-stacks-for-software-engineers/ 2026-09-14T03:55:06+00:00 https://freesoftware.blog/wp-content/uploads/2026/09/featured-image-5.jpg https://freesoftware.blog/memory-bound-how-memory-bandwidth-shapes-local-llm-speeds/ 2026-09-13T03:55:11+00:00 https://freesoftware.blog/wp-content/uploads/2026/09/featured-image-6.jpg https://freesoftware.blog/building-reliable-offline-applications-with-fully-open-weights/ 2026-09-12T03:55:20+00:00 https://freesoftware.blog/wp-content/uploads/2026/09/featured-image-7.jpg