511–520 of 620 posts
For personal use, yes. I replaced a $100/m subscription to claude in favor of running pi harness pointed at unsloth studio, using both qwen (unsloth/Qwen3.6-35B-A3B-MTP-GGUF) and gemma (unsloth/gemma-4-26B-A4B-it-GGUF) models, depending on my mood. I have a machine I built about 5 years ago with dual RTX3090s in it (I was going to build a new gaming machine anyways, and the llama release had just dropped so I tacked…
Earlier quoted context omitted.
Here's a DeepSeek-V4-Flash benchmark on 2X RTX Pro 6000: - Prefill: ~10K tok/s - Decode: 190 | 375 | 980 tok/s (for 1 | 4 | 16 concurrent requests) - GPU power draw during benchmark: Average: 585W | Max: 849W | Limit: 1200W with undervolt. Idle PC is 125W. I've asked it to calculate the following considering a realistic blend of cached prompts and decode for agentic dev scenario. Electricity-only (@ USD $0.08/kWh) Us…
Interestingly if we assume 16 concurrent users, prefill drops to 600 t/s and generation to 61 t/s, and this starts to be dangerously near to M5 Max 35 t/s generation and 400 t/s prefill you get with DwarfStar in your own laptop (that you use for many other things) that costs ~6500 usd/eur.
Of course this requires wide enough batches to have at least some reuse of fetched experts across a batch, but that seems feasible in the "unattended" case, where firing off multiple inferences to be processed together seems quite natural. (We may also have some benefit from better use of the resident experts cache and/or of SSD transfer bandwidth.)
https://github.com/antirez/ds4/issues/275 seems to provide intriguing rough results while https://github.com/antirez/ds4/issues/314 is a valuable contrast where one commonly suggested solution ("just run multiple instances of the engine in parallel") ran into real issues. Neither of these discuss the combined use of batching and SSD streaming yet, so there's room for experimentation.
Earlier quoted context omitted.
I am right there with you. Mind-boggling. It's a indistinguishable from magic technology!! I tried running some basic tasks through Qwen with Opencode on a 10 year old dual Xeon server for shits and giggles. I gave it a simple task like "use ffprobe first but convert this webm to mp4" and it was able to complete the task with zero network calls outside my network. On 10 year old hardware. It took about 3 minutes to c…
> You're gonna be googling the CLI switches for at least 10 minutes So there's this really amazing program called "man"
Yes, you surely can read man, docs, whatever, then DIY. The point is that in many areas people don’t really want to become an expert, like in ffmpeg cli arguments, they just want the work to be done. Above is an example of agent being able to do it locally, and I think it’s great
I have! I care about data privacy and LLMs being free. I'm using the Pi coding harness but containerized and sandboxed, to make sure it's running completely offline. On my Mac Studio with 128GB RAM (or MacBook with 36GB RAM) I'm using Qwen3.6 35b, with only 3b active parameters so that it runs really fast. I've done a complete redesign for my website's homepage and blog with Django + Wagtail. The latter is interestin…
I can use Gemini 3 Flash with the harness I built for around 8 years and still not exceed the cost of a Mac Studio with 128GB, the price for privacy is very high. Agentic flows that get stuck can be worked around but I prefer developer velocity.
Earlier quoted context omitted.
What kind of coding do you do? Do you keep track of frontier models to vibe check the differences and re-evaluate constantly or are you ok with having a nerfed model forever? (not being judmental, just really wanto to know your framework here)
Some of the work I do, I do for an (EU) organisation that doesn't have clear rules or guidelines on the use of AI yet. Though I have seen colleague-developers blatantly putting source code into external Claude-like models, I stay true to my principles and don't. I know for certain that everything that I run through my local, offline Pi Container Sandbox cannot leave the machine, and thus can't result in a data breach…
Another POV is that most of the code written in most of my codebases were generated by Codex/Claude, so they would be "stealing data from themselves" in a sense.
I've been working with Transformers/LLM training in 2018-2021 and then now, more recently again. Things are far different. I think they would be more interested in the "how" you got your code to be satisfactory with your guidance than the actual code generated. But mostly I personally trust that they are not really using my trajectories for that (unless I explicitly allow it in the configs)
Earlier quoted context omitted.
> you really need to know what you're asking, and be precise Any chance that you could share some recent prompts to give other HNers a head start on his to approach Qwen? If you are uncomfortable posting them here, my Gmail username is the same as my HN username. Thank you.
I'm glad you're asking. I already started writing a blog post on how to best make use of local models. I'll share it as soon as I have a complete enough list. If anyone else reading this would like to chime in with their tips & tricks, let us know! For the time being, off the top of my head, I'd say: - Prompt Engineering tips & tricks apply here (like being complete in the relevant context you provide in your questio…
I do mostly scripting, devops, data processing and systems stuff (ansible playbooks, managing network devices, deploying new software for various things that involves reading docs, writing helm charts, modifying existing ones etc).
All other models Gemini, Chatgpt, grok and all OS models don't come even close. I'd rather use Sonet than Qwen.
It's a sad reality. I was thinking about implementing maybe some sort of "sanity checking" by running every prompt twice on two different models doing sanity checking of the first on the second.
Elaborate knowledge systems help a little, but personally I think Anthropic must be doing something "clever" with its models (processing via multiple models etc). Nothing else in my mind explains the discrepancy.