Qwen 3.6 27B is the sweet spot for local development - Quesma Blog

kept by eddie jun 30

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.

Alibaba's small, open source Qwen3.5-9B beats OpenAI's gpt-oss-120B and can run on standard laptops
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.
also on Alibaba, #benchmarks, #open-source, #developer-tools
How to run Qwen 3.5 locally
Hacker News commenters share experiences and benchmarks for running Qwen 3.5 locally, covering hardware choices, quantization trade-offs, and practical coding performance.
also on Llama.cpp, #benchmarks, #hardware, #open-source, #developer-tools
GitHub - alibaba/open-code-review: Battle-tested at Alibaba's scale. Hybrid architecture code review tool: deterministic pipelines + LLM Agent, precise line-level comments, built-in fine-tuned ruleset (NPE, thread-safety, XSS, SQL injection), OpenAI & Anthropic compatible.
Alibaba's Open Code Review is a hybrid CLI tool combining deterministic pipelines with an LLM agent for precise, token-efficient code reviews at scale.
also on Alibaba, #open-source, #ai-coding, #developer-tools
AI At Home Part 2: Multi GPU Drifting
The author boosted Deepseek V4 Flash inference from ~10 to ~20 tokens/sec on four e-waste AMD V620 GPUs by using layer parallelism and a speculative draft model.
also on Llama.cpp, #hardware, #open-source, #ai-coding, #developer-tools
Introducing Supabase Evals
Supabase open-sourced evals, a benchmark testing AI coding agents on real Supabase tasks like schema building and debugging, to measure and improve agent performance across its platform.
also on OpenCode, #open-source, #ai-coding, #developer-tools