161–170 of 286 posts
Earlier quoted context omitted.
Claude code is designed for anthropic models. Try it with opencode!
I will, right now. EDIT: opencode was a bit slow with qwen3.5:35b using Ollama. Faster/nicer to use with Liquid lfm2:latest
this is bullshit with a kernel of truth. none of the qwen 3.5 models are anywhere near sonnet 4.5 class, not even the largest 397b. BUT 27b is the smartest local-sized model in the world by a wide wide margin. (35b is shit. fast shit, but shit.) benchmarks are complete, publishing on Monday.
I am a total neophyte when it comes to LLMs, and only recently started poking around into the internals of them. The first thing that struck me was that float32 dimensions seemed very generous . I then discovered what quantization is by reading a blog post about binary quantization. That seemed too good to be true. I asked Claude to design an analysis assessing the fidelity of 1, 2, 4, and 8 bit quantization. Claude…
Mind sharing any resources? I've been thinking about trying to understand them better myself.
Earlier quoted context omitted.
> Wonder what am I doing wrong? You're comparing 100b parameters open models running on a consumer laptop VS private models with at the very least 1t parameters running on racks of bleeding edge professional gpus Local agentic coding is closer to "shit me the boiler plate for an android app" not "deep research questions", especially on your machine
The hardware difference explains runtime performance differences, not task performance. Speculation is that the frontier models are all below 200B parameters but a 2x size difference wouldn’t fully explain task performance differences
Some versions of some the models are around that size, which you might hit for example with the ChatGPT auto-router.
But the frontier models are all over 1T parameters. Source: watch interview with people who have left one of the big three labs and now work at the Chinese labs and are talking about how to train 1T+ models.
this is bullshit with a kernel of truth. none of the qwen 3.5 models are anywhere near sonnet 4.5 class, not even the largest 397b. BUT 27b is the smartest local-sized model in the world by a wide wide margin. (35b is shit. fast shit, but shit.) benchmarks are complete, publishing on Monday.
Will check your updated ranking on Monday.
Earlier quoted context omitted.
"Create a single page web app scientific RPN calculator" Qwen 3.5 122b/a10b (at q3 using unsloth's dynamic quant) is so far the first model I've tried locally that gets a really usable RPN calculator app. Other models (even larger ones that I can run on my Strix Halo box) tend to either not implement the stack right, have non-functional operation buttons, or most commonly the keypad looks like a Picasso painting (i.e…
is your prompt literally 1-sentence? if so, a better approach would be to ask it to first plan that entire task and give it some specific guidance then once it has the plan, ask it to execute it, preferably by letting it call other subagents that take care of different phases of the implementation while the main loop just merges those worktrees back it's how you should be using claude code too, btw
Earlier quoted context omitted.
Not exactly, but pretty close: https://artificialanalysis.ai/models/capabilities/coding?mod... Somewhere between Haiku 4.5 and Sonnet 4.5
Looks much closer to Haiku than Sonnet. Maybe "Qwen3.5 122B offers Haiku 4.5 performance on local computers" would be a more realistic and defensible claim.
Thinking about getting a new MBP M5 Max 128GB (assuming they are released next week). I know "future proofing" at this stage is near impossible, but for writing Rust code locally (likely using Qwen 3.5 for now on MLX), the AIs have convinced me this is probably my best choice for immediate with some level of longevity, while retaining portability (not strictly needed, but nice to have). Alternatively was considering…