AI Briefing#llama-server
The latest AI and developer news about #llama-server, with the original source and a short summary.
The latest AI and developer news about #llama-server, with the original source and a short summary.
The update breaks compatibility for users relying on the previous 8080 default or hardcoded harness configurations.
By applying MTP to the Qwen3.6-35B-A3B model, a decoding speed improvement of about 1.49x was achieved on llama-server.
On AMD Strix Halo, Mistral Medium 3.5 took about 2 hours to process a 48k prompt.
Connecting Qwen3.6 to Claude Code on a dual 3090 setup cut the estimated 8-hour cost from $142 to under $4.
Qwen3.6-27B is a 27B dense model that claims coding performance surpassing the previous ultra-large MoE flagship.
Shared a setup for running Qwen3.6-35B-A3B with llama-server on an RTX 4060 8GB VRAM, along with a thinking budget pitfall.
Built a paper-based web app with Qwen3.5 35B and confirmed it maintains context well up to 70-80K tokens.
Shared real-world benchmarks and issues from running Qwen3.5-27B on the Arc B70.