Hackernews posts about Qwen 4B
- Qwen 3.5 9B, 4B models beating 30B, 80B models (huggingface.co)
- Qwen 3.5: 9B, 4B, 2B, 0.8B (huggingface.co)
- Teaching Qwen3-4B to Trade: From Hold-Collapse to +9.4% Returns (sabareesh.com)
- Latest progress helping Qwen3-4B Learn (github.com)
- Show HN: Open-Jet – self-hosted Agentic TUI for air-gapped Jetsons (www.openjet.dev)
- Show HN: I made Qwen3.5-4B 13% smarter by compressing it to 4-bit (huggingface.co)
- According to benchmarks Qwen3.5 4B is as good as GPT 4o (twitter.com)
- Qwen3.5 Small: 0.8B, 2B, 4B, 9B Released (huggingface.co)
- Training Qwen 4B to Beat Large Models on Work Tasks (neurometric.substack.com)
- Show HN: Distilled 0.6B text-to-SQL model (github.com)
- Qwen3-4B-Thinking-2507 (huggingface.co)
- 4B parameter Deep Research model based on Qwen (huggingface.co)
- Show HN: KARMA – An evaluation framework for Medical AI systems (karma.eka.care)
- Qwen3-4B-Thinking: "This is art–pelicans don't ride bikes " (simonwillison.net)