Alibaba's small, open source Qwen3.5-9B beats OpenAI's gpt-oss-120B and can run on standard laptops

kept by eddie mar 03

Alibaba's Qwen3.5-9B outperforms OpenAI's 120B-parameter gpt-oss on benchmarks while being 13 times smaller and capable of running on standard laptops.

Jev is an honest game changer.
Jev, a constrained decision model, matched Grok's 89.6% accuracy on 48 game questions while cutting latency 84% and cost 88.5% by using a selective Gemini fallback.
also on gpt-oss-120B, #developer-tools
GitHub - jaredpalmer/kev: tiny Jev-like family of decision models built on top of Qwen3.5 you can train and run on your own
Kev provides small, trainable decision models based on Qwen3.5 that support multi‑question System One API and can be run locally.
also on Qwen3.5, Hugging Face, #open-source, #ai, #developer-tools
Running LLMs in the Browser with Three.js
Three-LLM enables running GPT-2, SmolLM2, Qwen, and Phi language models in the browser by converting their inference graphs into Three.js TSL compute shaders on WebGPU.
also on Qwen3.5, Hugging Face, #open-source, #developer-tools
Qwen 3.6 27B is the sweet spot for local development - Quesma Blog
Qwen 3.6 27B with llama.cpp runs at usable speeds on Apple Silicon and Nvidia RTX hardware, making it the first local model practical for coding development.
also on Alibaba, #benchmarks, #open-source, #developer-tools
GitHub - alibaba/open-code-review: Fast, efficient, battle-tested at Alibaba's scale. Hybrid architecture code review tool: deterministic pipelines + LLM Agent, precise line-level comments, built-in multi-language ruleset (NPE, thread-safety, XSS, SQL injection), OpenAI & Anthropic compatible.
OpenCodeReview is Alibaba’s open-source CLI tool that combines deterministic pipelines with an LLM agent for precise, line‑level code reviews, supporting multiple languages and low token usage.
also on Alibaba, OpenAI, #open-source, #developer-tools