[GUEST ACCESS MODE: Data is scrambled or limited to provide examples. Make requests using your API key to unlock full data. Check https://lunarcrush.ai/auth for authentication information.]

@JustinLin610 "we'll do something today to help u save some money. but plz don't open up qwen-code in ur home dir"
@JustinLin610 Avatar @JustinLin610 on X 2025-07-24 07:41:19 UTC 27.5K followers, 71.3K engagements

"gotta sleep early. tmr (oh i should say today) is qwen3-235b-a22b-thinking-2507 if everything goes well"
@JustinLin610 Avatar @JustinLin610 on X 2025-07-24 18:51:54 UTC 27.5K followers, 247.3K engagements

"the thinking model finally comes at the end of this week. okay we ve made some improvements on qwen3 to make this thinking 2507. better perf on a number of tasks and more generalized perf. hope it can solve some problems that u met with qwen3-235b-a22b. but i have to say there might still be much room for us to improve on thinking. it is smart but sometimes it is still too talkative or falls into some pits. that's all for today. c u next week we still have a lot of gifts for u guys"
@JustinLin610 Avatar @JustinLin610 on X 2025-07-25 10:20:18 UTC 27.5K followers, 49.4K engagements

"actually u can use qwen3-coder for free in qwen chat through web mobile app desktop app. download apps through"
@JustinLin610 Avatar @JustinLin610 on X 2025-07-24 18:24:55 UTC 27.5K followers, 18.7K engagements

"let's have a small desert Qwen-MT provided by Alibaba Cloud API. this is a specialized model good at translation and it runs fast. enjoy"
@JustinLin610 Avatar @JustinLin610 on X 2025-07-24 15:42:18 UTC 27.5K followers, 23.1K engagements

"A small update on Qwen3-235B-A22B but a big improvement on its quality We thought about this decision for a long time but we believe that providing better-quality performance is more important than the unification at this moment. We are still continuing our research on hybrid thinking mode but we this time ship separate models for you Qwen3-235B-A22B-Instruct-2507 has much more comprehensive knowledge and capabilities than the previous release and I think you might find it a better partner for you when you use it in Qwen Chat Oh don't forget it natively supports 256K tokens and with"
@JustinLin610 Avatar @JustinLin610 on X 2025-07-21 17:23:01 UTC 27.4K followers, 62.3K engagements

"Note that this is a non-thinking model. Thinking model on the way"
@JustinLin610 Avatar @JustinLin610 on X 2025-07-21 17:40:48 UTC 27.5K followers, 63.1K engagements

"Something big for Qwen2-VL: it is finally supported by llama.cpp We are testing it to make sure everything is okay and then we might provide GGUF to you all Can't wait to see its use in Ollama LMStudio etc. Check this PR for more details"
@JustinLin610 Avatar @JustinLin610 on X 2024-12-14 16:27:41 UTC 27.4K followers, 21.2K engagements

"@basedwebscraper @Alibaba_Qwen See if it happens this week"
@JustinLin610 Avatar @JustinLin610 on X 2025-07-21 17:23:41 UTC 27.3K followers, 1595 engagements

"why the world is so real: some people would like to put money in our pocket but got no way but some people don't want to spend money but get debts. we r so dumb and we really need to improve our product but anyway i take ur complaints and we'll try to make u happy"
@JustinLin610 Avatar @JustinLin610 on X 2025-07-24 07:55:29 UTC 27.5K followers, 29K engagements

"@juniorro16 just building a method to let you use it for free for multiple times"
@JustinLin610 Avatar @JustinLin610 on X 2025-07-24 10:26:45 UTC 27.5K followers, 1132 engagements

"@CancelledBigot this one is not good for u just shoot ur comments and we llsee how to fix"
@JustinLin610 Avatar @JustinLin610 on X 2025-07-24 07:56:36 UTC 27.4K followers, 2120 engagements

"it is on qwen chat choose Qwen3-235B-A22B-2507 press the thinking button then enjoy"
@JustinLin610 Avatar @JustinLin610 on X 2025-07-25 10:43:46 UTC 27.5K followers, 31.1K engagements

"@Fancyrocket we will keep updating the ckpt maybe next month idk"
@JustinLin610 Avatar @JustinLin610 on X 2025-07-24 12:24:04 UTC 27.4K followers, XXX engagements

"mcp finally there. funny i love qwen with tools ahah"
@JustinLin610 Avatar @JustinLin610 on X 2025-07-11 15:27:42 UTC 27.4K followers, 8374 engagements

"this is what is not small boys spent so much time building the Qwen3-Coder after Qwen2.5-Coder. it is much bigger but based on MoE and way stronger and smarter than before not sure we can say competitive with claude sonnet X but might be for sure a really good coding agent. hope u enjoy this model we'll take a rest tomorrow and then we will come back very soon nighty night"
@JustinLin610 Avatar @JustinLin610 on X 2025-07-22 21:16:38 UTC 27.5K followers, 57.8K engagements