Qwen (Квен) — модели и чат-бот Alibaba

I think we're cooked...

Honestly, tonight I had a realization moment. My token pan for qwen cloud expired, so I thought 'you know what, I wanna see what local AI can do'. For context, I'm working on my IDE, so I…

2x Tesla p100s, q6_k quant, Qwen 3.8 27B ~60tps

Running Qwen Code on a Custom OpenAI-Compatible API: modelProviders, a 41,000-Character First Request and Retries That Keep Going for Minutes

Qwen Code is the terminal coding agent from the Qwen team. It started as a fork of Gemini CLI, but unlike Gemini CLI it speaks the OpenAI Chat Completions format, so it can run against any…

Comparing Qwen and Gemma on the Low End: Qwen Is Faster Without Drafting, Gemma Has Better Quality

This article provides a step by step deployment guide for Qwen3.5-2B to a local, desktop and laptop hosted GPU enabled system, served by llama.cpp beside Gemma 4 E2B on the same cards. A…

One sentence in, a website out: a $0.03-a-site side hustle on a fine-tuned Qwen3-8B and Gemma 4

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 2: Side Hustle What I Built A website service for small businesses that will never write a design brief. The owner…

MenuGlot: Offline AI Menu Maker for Local Restaurants

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 2: Side Hustle What I Built MenuGlot turns a photo of a restaurant menu into a clean, print-ready menu with English…

Qwen3.8-27B on the iPhone 18 Neural Engine at 15–70 tok/s (1.5 bpw)

My Q4 model said True where BF16 said False, so I diffed them layer by layer

Qwen3-0.6B in BF16 reads this: def is_prime(n): if n < 2: return and puts 97.9% on False. The Q4_K_M quant of the same model puts 79.1% on True. That's one token out of 1,282 I scored.…

Serving a 125B coding model to a team from one RTX 5090: what broke and what we tuned

If you have ever thought about replacing a per-seat AI coding subscription with a GPU you control, the first thing you want to know is not the benchmark score. It is how many people can use…

Однобитная Bonsai по весам: что видно при сравнении с Qwen и как получить такую модель дистилляцией

Хотели бы вы запустить большую языковую модель на видеокарте с небольшим объёмом памяти? Модель с 27 миллиардами параметров, упакованными в 16 бит, занимает около 54 ГБ. Если хранить каждый…