CLOB release tomorrow at 12:10pm UTC As mentioned in our update earlier this week, this is one of the releases aimed at latency improvements. Expect a brief restart with up to ~10 minutes of downtime. Status updates:

☕️ Releases are now generally available in Plane. - Group work items from any project under a named release - Progress bar updates as work item states change - Write and publish the changelog on the same page - Tag items with a Release custom property Two new custom property types ship alongside, - Release picker, which automatically routes work items into a release's Scope tab. - Formula field, which computes values from other properties on the work item. Day 3, launch week. ☕️ Step inside our coffee launch week - Read more about Releases -

We released experimental MTP Qwen3.6 Unsloth GGUFs! Qwen3.6 27B MTP now runs at 140 tokens/s. Qwen3.6 35B-A3B MTP gets 220 tokens/s generation on a single GPU. Qwen3.6 27B and 35B-A3B have >1.4x speed-up over the original GGUFs without any change in accuracy. Guide + GGUFs + Benchmarks: In terms of average speedup, we see a 1.4x for dense models at draft tokens = 2 and for the MoE around 1.15 to 1.2x. We do not recommend more than 2 draft tokens because the acceptance rate drops precipitously from 83% to 50% with 4 draft tokens, and the forward passes for MTP become less beneficial. Use `--spec-type mtp --spec-draft-n-max 2` Thanks to Aman for

Higgsfield releases Virality Predictor What does it mean: > Upload any clip up to 15s > Get viral potential, hook score & hold rate > See a heatmap of brain regions your clip activates > Pair with Ad Reference for recreated videos Available via MCP/CLI and on the platform.