Every processed story in chronological order, with the newest coverage first. Filter by tag, source, or score to drill in.
North Mini Code 1.0 brings an Apache 2.0-licensed agentic coding model with a low active-parameter footprint (3B of 30B) to the open-source ecosystem, making it freely usable and modifiable for local and commercial deployments.
The switch to SearXNG removes TinySearch's dependency on a single third-party search provider, addressing the fragility that made DuckDuckGo rate-limiting a blocking issue for agent workflows that rely on consistent web-search access.
Omi Med STT v1 is the best-performing locally-running open model on this benchmark, achieving cloud-competitive M-WER at 0.6B parameters while keeping patient audio entirely on-device.
This benchmark directly addresses a gap the post identifies — the lack of tool-calling quality evaluations for popular local GGUF quants — and provides concrete, reproducible evidence that KV cache quantization level and context length have measurable effects on tool-calling accuracy for Qwen3.6-35B-A3B.
Developers running local models should evaluate whether their agent scaffold — not just the model itself — is the bottleneck, as `little-coder` demonstrates that the right harness can close much of the gap between local and cloud model coding performance.
Practitioners running local agentic coding workloads should weigh Qwen3.5-27B's token efficiency and speed against Gemma4-31B's perfect accuracy but extreme resource demands — over 10 hours of runtime and 70GB DRAM — before choosing a model for automated fix pipelines.