Atlassian & AI Tutorials and Best Practices

v0.5 of our Atlassian Qwen3.8-27B: beats v0.4, now with GGUF for llama.cpp and Ollama

v0.5 of the Qwen3.8-27B we fine-tune for Forge, Jira, Confluence and JSM is out. It beat v0.4 on every gate we measure, with no waiver needed this time, using a training method that fixed the one thing capacity kept breaking. GGUF versions for llama.cpp and Ollama, Q8_0 and Q6_K, are now published alongside the existing MLX release, parity proven across three separate measured links plus a served-model probe.

Mihai PerdumSep 20, 202611 min read

Atlassian Insights & Tutorials

Articles 1

v0.5 of our Atlassian Qwen3.8-27B: beats v0.4, now with GGUF for llama.cpp and Ollama

v0.5 of our Atlassian Qwen3.8-27B: beats v0.4, now with GGUF for llama.cpp and Ollama