Tagged "code-generation"
- Qwen 3.5 397B emerges as top-performing local coding model
- NVIDIA Nemotron Cascade 2 30B Delivers 120B-Class Performance in Compact Form Factor
- Cursor's Composer 2 Model Analysis – Fine-Tuned Variant of Kimi K2.5
- Kilo Is the VS Code Extension That Actually Works With Every Local LLM I Throw At It
- Qwen 3.5 122B Demonstrates Exceptional Reasoning for Local Deployment
- OmniCoder-9B: Efficient Coding Model for 8GB GPUs
- Fine-Tuned 14B Model Outperforms Claude Opus 4.6 on Ada Code Generation
- Local AI Coding Assistant: Complete VS Code + Ollama + Continue Setup
- Experiment: 0.8B Model Self-Improvement on MacBook Air Yields Surprising Results
- Show HN: Aver – a Language Designed for AI to Write and Humans to Review
- Qwen3-Coder-Next Achieves Top Ranking on SWE-bench at Pass@5
- Qwen 3.5-4B Generates Fully Functional OS in Single Prompt
- Qwen 3.5-35B-A3B Achieves 37.8% on SWE-bench Verified Hard
- Incrmd: Incremental AI Coding by Editing PROJECT.md
- Jan Releases Code-Tuned 4B Model for Efficient Local Code Generation and Development Tasks
- C7: Pipe Up-to-Date Library Docs Into Any LLM From the Terminal
- Qwen 3.5 Underperforms on Hard Coding Tasks—APEX Benchmark Analysis
- Agent System – 7 specialized AI agents that plan, build, verify, and ship code
- Qwen3.5-35B-A3B Emerges as Game-Changer for Agentic Coding Tasks
- Qwen3 Coder Next Remains Effective at Aggressive Quantization Levels
- Qwen3 Coder Next 8FP Demonstrates Exceptional Long-Context Performance on 128GB System
- Real-World Coding Benchmark Tests LLMs on 65 Production Codebase Tasks
- MiniMax Releases M2.5 Model with SOTA Coding and Agent Capabilities
- Optimal llama.cpp Settings Found for Qwen3 Coder Next Loop Issues
- Qwen Coder Next Shows Specialized Agent Performance
- I Tried a Claude Code Rival That's Local, Open Source, and Completely Free