Any plan to release on ollama?
Show HN: Needle2: 14MB agentic LLM for phones, wearables, smart home and robots
71–80 of 164 posts
Re: Show HN: Needle2: 14MB agentic LLM for phones, wearables, smart home and robots
#72This 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 particular…
So, its not a general language model, focused on tool call strictly for tiny edge-devices. There are solutions everywhere for high-capacity devices, Needle is for sub-$200 devices.
14mb? More like sub-$20 devices.
Re: Show HN: Needle2: 14MB agentic LLM for phones, wearables, smart home and robots
#73Earlier quoted context omitted.
So, its not a general language model, focused on tool call strictly for tiny edge-devices. There are solutions everywhere for high-capacity devices, Needle is for sub-$200 devices.
14mb? More like sub-$20 devices.
Most pi pico's come with 16mb of flash. I wonder what kind of performance that can eek out.
Re: Show HN: Needle2: 14MB agentic LLM for phones, wearables, smart home and robots
#74My 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?
Re: Show HN: Needle2: 14MB agentic LLM for phones, wearables, smart home and robots
#75Re: Show HN: Needle2: 14MB agentic LLM for phones, wearables, smart home and robots
#76Re: Show HN: Needle2: 14MB agentic LLM for phones, wearables, smart home and robots
#77This 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.
Re: Show HN: Needle2: 14MB agentic LLM for phones, wearables, smart home and robots
#78Funny result from the web demo. I'm well aware that it's an extremely small and, well, stupid, model, but even so: Query: HN Result: { "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 doe…
[dead]
Re: Show HN: Needle2: 14MB agentic LLM for phones, wearables, smart home and robots
#79My 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?
It's not a conversational model. It's meant as a local tool calling model.
Re: Show HN: Needle2: 14MB agentic LLM for phones, wearables, smart home and robots
#80Could 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?
There's a Manning book on creating your own LLM from scratch which answers your question exactly. There's another book from the same publisher specifically about small language models for specialty purposes.