Local LLMs are actually good now, and I wasted months not realizing it
…On the MMMU-Pro visual reasoning benchmark, Qwen3.5-9B scored 70.1, which is not far behind leading models like Gemini 3 Pro and GPT-5.4 that score in the…
Tracked topic
Qwen3 is an AI model family developed by Alibaba, released as a set of large language models for natural-language tasks.
…On the MMMU-Pro visual reasoning benchmark, Qwen3.5-9B scored 70.1, which is not far behind leading models like Gemini 3 Pro and GPT-5.4 that score in the…
…There are a couple of other mobile-optimized models worth flagging - Phi-4 Mini and Qwen3 1.7B both come up a lot, and I'm not ruling them out for future…
…Related I finally found a local LLM I actually want to use for coding Qwen3-Coder-Next is a great model, and it's even better with Claude Code as a harness…
…Related I finally found a local LLM I actually want to use for coding Qwen3-Coder-Next is a great model, and it's even better with Claude Code as a harness…
…Related I finally found a local LLM I actually want to use for coding Qwen3-Coder-Next is a great model, and it's even better with Claude Code as a harness…
…Related Qwen3.5-9B tops every AI benchmark right now, but that's not how you should pick a model There's a lot more to a model than just benchmarks. Qwen…
…Related I finally found a local LLM I actually want to use for coding Qwen3-Coder-Next is a great model, and it's even better with Claude Code as a harness…
…You feed it a .txt, .md, or .epub, an LLM chunks the text and annotates every line with a speaker and a voice direction, and then a local TTS engine (Qwen3-TTS…
To show you the most relevant results, we’ve omitted some entries very similar to those already shown. Repeat the search with the omitted results included.