Tracked topic
Qwen3 is an AI model family developed by Alibaba, released as a set of large language models for natural-language tasks.
…My Bachelor’s thesis was conducted on the viability of benchmarking the non-functional elements of Android apps and smartphones such as performance, and I’ve been working in the tech industry…
…I’m running an RTX 3070 with 8GB VRAM, and ended up swapping my 20B model for a 9B (qwen 3.5) and got noticeably better results. The reason is because of…
…It's a fork of an open-source Android LLM client, and I've been running it for a few weeks using my local LLMs, namely Qwen 3.6 27B and Qwen…
…Qwen's own 4B reportedly matches the previous generation's 80B on a lot of benchmarks, so "small" doesn't mean "bad", at least not the way it used to. This isn…
…My Bachelor’s thesis was conducted on the viability of benchmarking the non-functional elements of Android apps and smartphones such as performance, and I’ve been working in the tech industry…
…s a benchmark called IFEval that scores it out of 100. Granite 4.0 H 1B lands at 78.5 here, which is essentially neck and neck with Qwen 2.5 32B…
…My Bachelor’s thesis was conducted on the viability of benchmarking the non-functional elements of Android apps and smartphones such as performance, and I’ve been working in the tech industry…
…Qwen3-Coder-Next is still the local champion It did a great job for what it has I threw Qwen3-Coder-Next into the test partly because I wanted to see how…
…My Bachelor’s thesis was conducted on the viability of benchmarking the non-functional elements of Android apps and smartphones such as performance, and I’ve been working in the tech industry…
…They include Gemini, my local Qwen setup, and LibreChat. I used them for real everyday (non-coding) tasks, not benchmarks. So stuff like design work, research, doc analysis, and general back and…