Fine-tuned Qwen models run surprisingly well on NVIDIA Jetson hardware. We've deployed several 7B variants for edge AI tasks where latency matters more than raw accuracy – think industrial inspection, retail analytics where you can't rely on cloud connectivity. The key is LoRA fine-tuning keeps the model small enough to fit in unified memory while still hitting production-grade inference speeds. Biggest surprise was power efficiency; a Jetson Orin can run continuous inference at under 15W while a cloud round-trip burns way more energy at scale.
Very interesting. Could you give examples of industrial tasks where lower accuracy is acceptable?
Naive question, but could neural networks handle these use cases?
NTA but almost certainly, the advantage is that Qwen3.5 is extremely generic already so adapting it to a specific task is way easier than training a NN from scratch. It's probably akin to how OCR is now just something I use Qwen for even though I have access to dedicated OCR tools, Qwen is good enough and it's already in my vram. Modern VLLMs are pretty great at answering basic questions about an image by default and I'm guessing finetuning takes them from "pretty good" to "good enough to use in production".
> NVIDIA Jetson hardware ... 15W
7B on 15W could be any of the Orin (TOPS): Nano (40), NX (100), AGX (275)
Curious if you've experimented with a larger model on the Thor (2070)
> where latency matters more than raw accuracy – think industrial inspection
Huh? Why would industrial inspection, in particular, benefit from lower latency in exchange for accuracy? Sounds a bit backwards, but maybe I'm missing something obvious.
At a very high level, think fruit sorting[0] where the conveyor belt doesn't stop rolling and you need to rapidly respond, and all the way through to monitoring for things like defects in silicon wafers and root causing it. Some of these issues aren't problematic on their own, but you can aggregate data over time to see if a particular machine, material or process within a factory is degrading over time. This might not be throughout the entire factory but isolated to a particular batch of material or a particular subsection within it. This is not a hypothetical example: this is an active use case.
[0] https://www.youtube.com/watch?v=vxff_CnvPek
But that's not something you'd use an LLM for. There have been computer vision systems sorting bad peas for more than a decade[0], of course there are plenty of use cases for very fast inspection systems. But when would you use an LLM for anything like that?
[0] https://www.youtube.com/watch?v=eLDxXPziztw
Nobody said you would use an LLM for that. It's an example of a process where "industrial inspection, in particular, [would] benefit from lower latency in exchange for accuracy".
The point of their comment isn't that you would use an LLM to sort fruit. It was just an illustrative example.
The discussion was about fine-tuned Qwen models, not industrial inspection in general. I would also find it interesting to learn about what kind of edge AI industrial inspection task you could do with fine-tuned llms, not some handwavy answer about how sometimes latency is important in real time systems. Of course it is, so generally you don't use models with several billion parameters unless you need to.
The thread you're in broke away from the main discussion topic.
Again: Nobody is using LLMs to (for example) sort fruit. But there are some industrial processes that prioritize latency over reliability.
You would use a VLM (vision language model). The model analyzes the image and outputs text, along with general context, that can drive intelligent decisions. https://tryolabs.com/blog/llms-leveraging-computer-vision
But why would I want to results to be done faster but less reliable, vs slower and more reliable? Feels like the sort of thing you'd favor accuracy over speed, otherwise you're just degrading the quality control?
It's not that you want it to be faster, but you want the latency to be predictable and reliable, which is much more the case for local inference than sending it away over a network (and especially to the current set of frontier model providers who don't exactly have standout reliability numbers).
The high-nines of fruit organization are usually not worth running a 400 billion parameter model to catch the last 3 fruit.
Local, offline system you control is worth a lot. Introducing an external dependency guarantees you will have downtime outside of your control.
Right, but that doesn't answer why you'd need a fast 7b LLM rather than a slightly less fast 14b LLM.
In the hypothetical fruit sorting example, if you have a hard budget of 10 msec to respond and the 7B takes 8 msec and the 14B takes 12msec, there is your imaginary answer. Regular engineering where you have to balance competing constraints instead of running the biggest available.
....because sometimes people need a faster answer? There's many possible reasons someone might need speed over accuracy. In the food sorting example, if lower accuracy means you waste more peanuts, but the speed means you get rid of more bad peanuts overall, then you get fewer complaints about bad peanuts, with a tiny amount of extra material waste.
Hard real time is a thing in some systems. Also, the current approaches might have 85% accuracy -- if the LLM can deliver 90% accuracy while being "less exact" that's still a win!