Qwen3 4B
alibaba/qwen3-4b-instruct- Alibaba
- Family · Qwen3
- Released 28 Apr 2025
Not on OSMEXO yet
Scores · standing
Intelligence7.2#344/489
News & trends
13 mentions this week ▼ 19%this model · videos, posts, articles · 30 days
Trending · 14 days
- [Help] Mastik-KV transfer Qwen3-32B → Qwen3-4B on dual 5090, tried KV Bridge and results suck1 upvotes
- How AI Actually Learns: Watching Qwen3-4B Rewire on a GPU151 views
- I trained free local AI Ollama qwen3:4b-instruct to play Factorio. (more in desc)1.5K views
News · latest from Qwen3
- Memdoor: A team of 5 Qwen3.8-27B models beats Fable 5 on LiveCodeBench Hardgithub.com · 31 Oct
- Neuron Explorer for Qwen3.5-4B: See every neuron at work, make targeted editsgithub.com · 26 Oct
- How to train your own Jev for $17Together AI · 23 Sep
Benchmarks
bar = share of the top score · Benchmark data: Artificial AnalysisFamily progress
Intelligence Index
- Family releases33.7
Research papers
- Can LLMs Faithfully Solve Ontology Engineering Tasks? A Mechanistic Interpretability Study28 Oct
- Two Birds with One Stone: Skill-Augmented Generation via Unified Retrieval and Utilization28 Oct
- Think Twice: The Metis-1.6 Technical Report27 Oct
- When Is Additional Retrieval Worthwhile? A Cost-Aware Study of Evidence Gain and Answer Reliability in RAG27 Oct
- Folding Attention Biases into Keys Makes Compacted KV Caches Run on Standard Kernels27 Oct
- CANS: Capability-Preserving Neuron Steering for Large Language Models26 Oct
- Small agents should know what their tools do26 Oct
- SHIFT-JEV: Certified Abstention and Gain-Gated Continual Adaptation for LLM-Based Decision Models under Distribution Shift25 Oct
Social
Most watched and discussed · 90 days
- I trained free local AI Ollama qwen3:4b-instruct to play Factorio. (more in desc)Netbotic · 1.5K views · 24 Oct
- How AI Actually Learns: Watching Qwen3-4B Rewire on a GPULatent AI Labs · 151 views · 28 Oct
- Deslopped Qwen3-4B on 4-8GB GPUs: Is It Better?Tensor Garage · 73 views · 26 Oct
- Qwen3-4B with the AI writing tics cut out | Run It Yourself #ShortsChakkde AI News · 71 views · 22 Oct
- Spark 4B vs Qwen3-4B: Only One RanLab Coat AI · 60 views · 24 Oct
- Qwen3-4B at 1.641 Bits: Smaller Does Not Mean FasterTWO DOTS - Websites - E-Shop - SEO - Automation · 56 views · 21 Oct
- Show HN: Qwen3-4B with the AI writing tics trained out #ShortsDiario TECH-AI · 8 views · 22 Oct
- OrionKit with no API key: real terminal output from a local model (qwen3:4b-instruct on Ollama)RWD Industries · 4 views · 27 Oct
- Show HN: Qwen3-4B with the AI writing tics trained out #ShortsDiario TECH-AI · 4 views · 21 Oct
Same family
Qwen3- 6.0
- 6.9
- 6.1
- 5.2
- 13.1
- 9.5
Alternatives
other vendors · similar capability- 8.5
- 11.6
- 10.0
- 6.7
Want Qwen3 4B on OSMEXO?
Sign in to request it. Requests are reviewed; a request does not guarantee availability.