113
π
Is it still telling people to put glue on their pizza and convincing teenagers to kill themselves?
this post was submitted on 28 Jul 2026
113 points (90.6% liked)
Technology
43006 readers
106 users here now
This is the official technology community of Lemmy.ml for all news related to creation and use of technology, and to facilitate civil, meaningful discussion around it.
Ask in DM before posting product reviews or ads. All such posts otherwise are subject to removal.
Rules:
1: All Lemmy rules apply
2: Do not post low effort posts
3: NEVER post naziped*gore stuff
4: Always post article URLs or their archived version URLs as sources, NOT screenshots. Help the blind users.
5: personal rants of Big Tech CEOs like Elon Musk are unwelcome (does not include posts about their companies affecting wide range of people)
6: no advertisement posts unless verified as legitimate and non-exploitative/non-consumerist
7: crypto related posts, unless essential, are disallowed
founded 7 years ago
MODERATORS
This seems like a great time to mention what I built and hosted months ago. https://masland.tech/ai-efficiency-index/
The AI Efficiency Index tracks the cost/intelligence mix. Low intelligence is useless. Capability scales exponentially. Expensive β better value. MiMo-V2.5 is the leader.
If you have any questions feel free to ask. This uses the Artificial Analysis leaderboard. They have "cost per task" which I think is weird.
Which one of them made these overlapping bar labels?
Hey, a lot of people sucked making matplotlib plots before LLMs existed.
Probably alibaba with Qwen
Itβs a bit misleading.
Qwen 27B has way less βworld knowledgeβ than GPT-5. Ask it random trivia without internet search access, and GPT would know waaay more.
This is generally true of small vs large models.
β¦But honestly, Qwen 27B is better at tool use or agentic stuff. Itβs hyper optimized for just that and coding assistance, basically.
This is often true of old vs new. Most newer models have hyper focused on agents/coding, often to the detriment of other use cases.
Quantization for practically running Qwen 27V also has an impact. A off-the-shelf Q4_K_M is not the same as the unquantized weights in real-world use, or even an βoptimizedβ quantization like a custom exl3.
That's why you couple it with your own, self-hosted yacy or searxng instance. Embedded world knowledge does not help a model if it becomes outdated. I just let my agent research, embed that knowledge to a little Qdrant server, so other servers are not bothered again and pull the information from there when needed again. With a little RAG you can have GPT at home.
I mean baking knowledge into a model isn't really all that useful to begin with. Just download wikipedia locally and have it access it through tool use, it's way more efficient and more accurate. And yeah, I find Q6 tends to be the sweet spot where it's close enough to full 16 bit in performance, but doesn't chew up too much memory.
This is a pretty good idea I hadn't thought about. The whole wikipedia is about 37Gb.
yeah, it's not a completely insane amount of data, and a db like postgres can do fast text search on that too with fuzzy matching
If you run it with RAG (retrieval augmented generation), where the model includes web search, you get pretty decent results. I often include the phrase "search the web extensively for up to date information" in my prompts.
What version do you use and how do you run Qwen3.6? I've played around a bit with the Q4 version in LM studio +Zed, but I was not happy with the results. It looses track very often and often enters infinite loops or just stops...
I use an exl3, with 4 bit MLPs but higher bit depth attention layers. And I force some custom sampling so I can lower the temperature a bit while keeping it out of loops.
This wonβt work in LM Studio though. You have to run such a thing in TabbyAPI or some other backend that supports exllamav3.
Ok, thanks! Thaf sounds quite advanced, but I'll have a read afterwards :)
I sort of get it because of you know you're only using the model when you have Internet and want it to search then just let it.
Those models are for general use. If you have business use case and data related to it you can finetune model for specific use that will outperform all of frontier models and run at fraction of cost.
that's the other huge advantage of open models you can run locally
How can you run a local model for better coding support than fable/opus?
You can't right now because there is no dataset available for fine tuning. I'm just saying that it's possible to fine tune 8B-35B parameter model in int4 that will outperform those models ex. for single programming language and developer specific problems. You can read example of fine tuned 8B model here https://fermisense.com/when-machines-take-the-wheel/
load more comments
(3 replies)
what kinda hardware do you need to "run this on your desktop"?
A P40 with 24GB is ~150β¬, a V100 (32GB) is ~600β¬. Both of these fit Qwen3.6 27B (The P40 is about 3x slower though). The V100 even fits 400k context with a Q4 KV-Cache , which means you can have two slots for parallel processing (llama-cpp). You don't even have to use system memory. One of my inference servers is running with 8gb of DDR3 and a 2nd Gen i7, so my old hardware has a good use again.
thanks, good stuff! sadly, got none of these locally available.
I had to get mine from ebay and wait a couple weeks as they came from China too. Also I recommend having a 3D-Printer and some Blower-Fans on hand as you will either have to buy or print your own fan shroud for these server cards.
You need a GPU with around 16gb vram at a minimum to run qunatized version.
I run Qwen 3.6 27B quantized down to Q4_K_M or even a variant Q5_K_S on my 8gb VRAM entry level AMD GPU, with support of my CPU and 32gb system RAM. Yes, I also limit the Context Length heavily to something like 18k. It's slow. But the point is, you don't need necessarily 16gb VRAM.
But it's better to use faster models for this type of hardware anyway. The MoE type of models (such as 26B A4B, or 35B A3B) are vastly, vastly faster for normal usage, but they are a bit worse in some cases. Also Googles QAT trained model versions also have less RAM requirements without losing much quality.
I'm just saying that, so others are not discouraged too much. It's not the same experience as the full version off course, but you can use them with some tricks on weak hardware too.
I'm fairly optimistic that people will figure out how to optimize the models a lot further going forward. One obvious path is to try and separate the reasoning network from the trivia that gets baked into the model, and some work is being done in this area. If you could have a context free reasoning engine and then feed the facts it needs to know on the fly based on the context you're running it in, then you could likely have a much smaller model that's very capable.
load more comments
(3 replies)
according to performance on standard benchmark. somewhat covered by the controversy surrounding the term: benchmaxing.
if you see all benefit as a linear one dimensional height on a bar graph..
its almost like you assume that the previous model gave the same exact answer(same style) and the new mode gave the same exact answer PLUS additional useful information.
it might be convenient if measuring progress was so simple. but unfortunately/fortunately , it is not so simple .
the most important benchmark are the comparison of outcomes on the problems that YOU have & prompts that YOU can(will) write. nothing else matters for YOU.
- i admit benchmarks are well designed to objectively measure competence on challenging problems that require skill and really need only ONE correct answer.
Sure, a benchmark doesn't capture all the subtleties and different use cases, but it does give a general idea of the capabilities of a model. Obviously, you have to run the model and see if it does what you need. But the chart isn't really about the nuance, it's showing how drastically the efficiency of the models has improved in just a year. The fact that we can even reasonably compare a model you can run on a desktop to one that needed a data center just a year ago is phenomenal.
i see what your saying. i didnt mean to discredit standard benchmarks entirely.
i guess its obvious that it measures capability regardless of imprecision.
2 major proposed changes:
**first, i dont really know. aside from saying "benchmark your own prompt+usecase"
a proposed plan:
- approach one: pay attention and credit new or improved architecture designs and research.
- approach two: spend more attention on benchmarks. especially specific benchmarks ( that are not focused with industrial domain tasks.) **domain task pursuit, is useful!.. but it depends on if your interest align to popular domains.
- approach three: if willing to utilize remotely hosted models. rating should also take in consideration.. tools and everything else: websearch performance, RAG performance, smooth interface, pref/balance between speed vs comprehensiveness, cost (if relevant), etc.. .
Honestly, I think the most reasonable approach is just to see what other people's experience is like and which models are well regarded, then try them out and see which one is the best fit for what you're doing. You might not even need the top performing one necessarily, and speed or lower resource usage might be a bigger factor.
[citation needed]
This is for qwen 3.5, not 3.6, but the vram requirements are a little out there for most:
https://willitrunai.com/blog/qwen-3-5-27b-vram-requirements
16 to 55GB...
I mean that's high but not unreasonable, especially with unified ram machines
load more comments
(1 replies)
I bought two RTX 3060 with 12 Gb each for a total of 24Gb VRAM. Sionce the cards are not top shelf anymore for gaming, they can be had used in the 200β¬ range, so my setup was 400β¬ over the cost of my existing PC. My PC, while not last gen was already pretty beefy, with a Ryzen 9 and 64 Gb RAM. I think 400β¬ to have a pretty good local AI setup is not bad at all.
I very much regret getting a 3070, with only 8GB of ram... Only reason I am hesitant about 3060s is that dual cards will use more power, and the economics are already pretty dicey when the hosted models are being sold below cost.
I learnt a few years back that the most important driver in GPU. or any other non upgradable memory device obsolescence, is RAM. I got a banger of a deal a few years on a RX 480, but it was 4Gb, adequate at the time. The card was obsolete way faster than the 8GB. As for the power draw, are you planning to have your AI setup running 24/7? Nvtop (linux GPU monitoring app) reports 50-80% of the cards top power draw. There is also the fact that my data doesn't leave my setup.
At the time, it wasn't clear that VRAM beyond 8GB was beneficial. Most cards at the time had basically capped at 8 for ages, and I wanted performance for ray tracing. In hindsight it was a bad call, but for gaming it made sense.
Not 24/7, I'd just start my PC when I need it, but its still more power than I'd like.
Keeping data local does make sense, which is why I have been toying with it. I can run relatively stepped on gemma4 models in 8GB, so for now, I'm happy, but im definitely looking at a Nvidia P40 as a second card.
load more comments
(4 replies)
view more: next βΊ