Show HN: Needle2: 14MB agentic LLM for phones, wearables, smart home and robots

This is cool. I definitely think the "micro" sized LLM space is underappreciated, so it's always good to see work like this. I foresee a paradigm in some contexts where you have a hierarchy of LLMs, with more competent models actively training smaller models to solve specific tasks very efficiently, and something like this could be the smallest layer in that stack.With that being said, the web demo is not particularly impressive. It really doesn't like anything I throw at it. I'm fine with accepting that fine-tuning is the solution to this, but I wonder if there's anything to gain from a bigger model? I know it's completely counter to the whole point of this, but a 14MB binary using 28MB of RAM seems unnecessarily small and pretty arbitrary.Like, what does a 28MB binary get you? Or a 140MB binary? Or a 1.4MB binary? I'm guessing the choice of 14MB came from minimizing the size as much as possible while meeting certain requirements/performance expectations, but even a Pi 5 has plenty more room to spare. Curious if there's a good explanation for this (which I may have missed in my skim of the post). reply:...

My first query:> Make it a little warmer in here.The reply:> "name": "set_thermostat", > "arguments": { > "temperature": 65, > "mode": "cool", > ... > "reasoning": "'warmer' implies need for cooling; set_thermostat with temperature 65 (typical warmth) and mode 'cool'.",Maybe I'm doing it wrong? reply: It's not a conversational model. It's meant as a local tool calling model.

Funny result from the web demo. I'm well aware that it's an extremely small and, well, stupid, model, but even so:Query: HNResult:{ "function_calls": [ { "name": "lock_door", "arguments": { "door": "front door" } } ], "reasoning": "User wants to lock the door. No specific door mentioned, so use 'front door' as default.", "confidence": 0 }I'd expect it to at least ignore (call no tools) for the queries that it doesn't understand. And it seems like it does do that, just not consistently. reply: The website says the model is for "tool calling, device use, and structured extraction". Your example just doesn't seem to be very relevant. FWIW, it did a pretty good job for tool calling when I tried it, and I think it could be pretty nice to have this running on locally and integrate with Home Assistant.

Could someone please share how such open source micro-LLMs might have been created?Do the creators take something like DeepSeek, and then delete most of the neurons to whittle down the size? reply: Another option for something this small and narrowly specialized could be to get traditional LLMs to synthesize the training data. Model collapse is probably less of an issue at this size relative to terabyte sized models.

That's really cool - I was already thinking of compressing `functiongemma-270m-it` down to 1-2 bits so it would work flawlessly in the browser. Your `Fine-tuning` feature is even much more convenient.

I tested with import needle @needle.tool def add(a: int, b: int): "Add two numbers." return a + b agent = needle.Needle(tools=[add]) print(agent.run("calculate 1 + 1?")["reasoning"]) python main.py No calculator or math tool available.conclusion: completly useless reply: Try the following tool description: "Calculate the sum of two numbers. Use for any arithmetic or math question." instead of "Add two numbers." Let me know how it goes, thanks!

> turn on the tv{ "function_calls": [ { "name": "lock_door", "arguments": { "door": "tv" } } ], "confidence": 0.0158 }Very interesting, seems confidence is 0 when tool calls are right?

This is cool!While most of the industry focuses on the frontier of “intelligence” (function), a release like this represents the frontier of the other end of the spectrum (form).Both are important if we ever want to see “Opus-level” capability running locally on commodity machines in the future. reply: agreed, this is where we have the biggest opportunity for innovation.

This is very interesting! I'm going to spend some time with this. This is really the only class of LLM I'm interested in at all. I sincerely hope on-device takes over and everyone looses their asses on these data centers.

Congrats on this release. The WASM implementation is really cool. This is a surprisingly good fit for a lot of cases, and I totally want to try turning this into a helper assistant for an application.Please, though, take a pass at humanizing the text on the page. It's Clauded up all over and makes it hard to read.

Makes me think of the demo from some time ago where someone got a ~29M parameter model running on an esp32. I wonder what kind of throughput this could get if a handful of esp32s were strung together...Edit: I have a pile of d1 minis, but not much time.

This is really cool, I'm curious how much knowledge can their be in smaller models? It seems the current trade off is you need sizeably larger models for more performance but I'm curious if in your work how far this is true, as edge ai is really what needs to get better before physical ai can take off (my two cents).

I wonder if there's any way to get this to plan out a dag of tool calls? i.e. use the results from earlier calls as the parameters to later ones? I tried introducing a stack based system, but gave up pretty quickly.

Was really cool to see yous use Engrams to cut down compute!Given its basically an O(1) lookup with disk space being the main constraint, I was curious if you've tried ablating engram layers and sizes across your setup?Also, why mHC over attention residuals?

Naïve and clumsy question: how would you pair this with speech-text-speech stuff, wake words etc.? Are there good examples of this for a Pi 5?The demo is super — I'm just having trouble seeing the whole picture for e.g. a screenless device.ETA: pun not intended

Looking forward to npm version of needle-rs supporting v2. I added needle support for tool use in my side project.

Any instructions available for running this on an ESP32-S3 or P4 like the site says?

I’d be interested in attempting to run this in a network- enabled 32MiB RAM microVM.

"make it as dark as possible" { "function_calls": [ { "name": "set_thermostat", "arguments": { "temperature": 72, "mode": "cool", "room": "living room" } } ], "reasoning": "'as dark as possible' -> set_thermostat to warm; 'dark' implies higher temperature; 'cool' mode for darkness.", "confidence": 0 } ... maybe this counts as dark humor at least.Since it seems limited to matching a few templates and otherwise falling flat on its face, I wonder how 14MB of regexes would fare in its stead. Normally you wouldn't want to parse arbitrary natural language input with regex because of how tedious and brittle it would be, but for the tedium we have LLMs and this alternative isn't exactly robust either.

The learned confidence gate is the crucial piece for a 14MB action model. On ambiguous requests such as the HN example, what calibration target decides between abstaining locally and escalating to the cloud?

What is the difference between this and random sentence generator?

what does the first L mean in LLM?