Offlined announces version 1.0.4 with Qwen models

// 4h agoPRODUCT UPDATE

Offlined announces version 1.0.4 with Qwen models

Offlined has announced the upcoming release of version 1.0.4 in October, which will introduce several cutting-edge local AI models released after August 2026. The update will feature the Qwen 3.8 27B model for powerful machines, the Qwen3.5 4B and 9B models for less capable hardware, and the return of the original model that started the project.

// ANALYSIS

This update demonstrates a balanced approach to local AI, catering to both high-end hardware enthusiasts and those with more modest setups.

–The inclusion of Qwen 3.8 27B provides top-tier local performance for advanced users.
–By adding Qwen3.5 4B and 9B, the team ensures the tool remains accessible to users with average hardware constraints.
–Bringing back the original model shows a commitment to the project's roots and early community.

// TAGS

local-aiofflinedqwenllm

DISCOVERED

4h ago

2026-09-22

PUBLISHED

4h ago

2026-09-22

RELEVANCE

6/ 10

AUTHOR

Offlined_org

// KEEP READING

More AI developer news from the feed

EXPLORE FULL FEED

UPDATE24m ago

Grok Bot desktop app ships 53 performance improvements

The desktop application for Grok Bot has shipped 53 performance optimizations over the past few days to dramatically reduce latency across core workflows. Key improvements include cutting network reconnection times after a flaky connection from 60 seconds to 0.7 seconds, reducing laptop wake recovery from 23 seconds down to 1 second, and bringing the transition time when switching back to the Computer view down to 868 milliseconds.

INFRA1h ago

Boat ships small 5GHz agent sandboxes

Boat has rolled out its small sandbox tier featuring 2 vCPUs clocked at 5GHz, 4GB RAM, and 12GB disk for $0.000005 per second ($0.018/hour). The persistent Ubuntu environments target AI agent workloads with zero-disk-cost snapshots, preinstalled devtools, and concurrency scaling up to 2,000 instances.

INFRA1h ago

Astra finds 14-year-old libuv memory leak

After investigating intermittent ChatGPT desktop crashes on macOS, developer Peter Steinberger prompted AI agent Astra to inspect system crash logs and trace native stack traces down to a 14-year-old memory leak in libuv's Darwin filesystem watcher. Pull request #5283 resolves the bug by releasing uncollected Core Foundation objects and C path buffers across exit paths in `uv__fsevents_reschedule`, halting quadratic memory growth during watch churn.

Offlined announces version 1.0.4 with Qwen models