Hackernews posts about SmolLM2

RSS feed for SmolLM2

01
newShow HN: IttyBittyAI – Qwen2.5:0.5B running on a 2017 Asus smartphone
▲ 2spottedmarley 11d discuss
02
newEvaluating smolvm as a sandbox for untrusted Python and JavaScriptsimonwillison.net
▲ 2binsquare 13d discuss
03
newShow HN: Smolvm – MicroVMs with CRIU Functionalitysmolmachines.com
▲ 1binsquare 18h discuss
04
newShow HN: VisionLaya: Jev with Vision capabilitieshuggingface.co
▲ 5someguy101010 16d 💬 2
05
newAnalysing 2048 on a 3×3 boardwww.chiark.greenend.org.uk
▲ 4rowbin 23d discuss
06
newShow HN: TripTended – Track what's still unresolved before a trip departstriptended.com
▲ 1smallmartial 5d discuss
07
newSmolLM2simonwillison.net
▲ 110edward 703d 💬 47
08
newThe Bunny B1: Demoing a Natrual Language to App Call Interface with SmolLM2github.com
▲ 14CountBayesie 699d discuss
09
newSmolLM2 (LLM) running in browser and WebGPUsimonwillison.net
▲ 2tristanMatthias 674d discuss
10
newSmolLM2: The new best smol models for on-device applications (all in the open)twitter.com
▲ 2pixel_sp 704d discuss
11
newSmolLM2: The new, best, and open small language modelhuggingface.co
▲ 1pixel_sp 704d 💬 1
12
newSmolLM2: When Smol Goes Big – Data-Centric Training of a Small Language Modelarxiv.org
▲ 1rahimnathwani 607d discuss
13
newHugging Face and Pruna AI: SmolLM2, Now 7x Smaller and 2x Fasterwww.pruna.ai
▲ 1bertrand_charp 638d discuss
14
newStructured Generation with SmolLM2 running in browser and WebGPUsimonwillison.net
▲ 1testerui 675d discuss
15
newsmollm2ollama.com
▲ 1tosh 703d discuss
16
newBypassing Gemma and Qwen safety with raw stringsteendifferent.substack.com
▲ 140teendifferent 260d 💬 46
17
newShow HN: Chrome extension to run DeepSeek, LLMs and Whisper locally in browsergithub.com
▲ 10tantara 610d 💬 2
18
newShow HN: Docker Model Runner Integrates vLLM for High-Throughput Inferencegithub.com
▲ 7ericcurtin 319d 💬 1
19
newShow HN: Chrome extension to run GenAI models in browsergithub.com
▲ 4tantara 611d discuss
20
newShow HN: Experiments Mapping the "Primitive Layer" in Language Modelsgithub.com
▲ 2dchisholm125 204d discuss
21
newShow HN: I wrote an LLM inference engine in pure Go – 48 tok/s zero dependenciesgithub.com
▲ 2computerex 213d discuss
22
newShow HN: Running LLM on smartwatch – found llama.cpp loading model twice in RAM
▲ 1perinban 187d discuss
23
newShow HN: Go LLM inference with a Vulkan GPU back end that beats Ollama's CUDAgithub.com
▲ 1computerex 212d discuss
24
newUsing pip to install a Large Language Model that's under 100MBsimonwillison.net
▲ 24sahli 606d 💬 5
25
newSmollm3: Smol, multilingual, long-context reasoner LLMhuggingface.co
▲ 388kashifr 454d 💬 79
26
newShow HN: Cactus – Ollama for Smartphonesgithub.com
▲ 231HenryNdubuaku 452d 💬 82
27
newShow HN: Off Grid: On-device AI-web browsing, tools vision,image,voice–3x faster
▲ 12ali_chherawalla 223d 💬 5
28
newShow HN: Open-source turn detection model for voice AI
▲ 8russ 651d 💬 1
29
newLLMs Are Moving Local – So Why Are We Still Paying for Tokens?
▲ 3josephinepqt 341d 💬 3
30
newShow HN: EdgeAI-OS – Air-gapped Linux distro where AI is a system primitive
▲ 2neuralweaves 239d 💬 2
31
newShow HN: Open-source multimodal AI that runs in the browserjohnjboren.github.io
▲ 2EschatonCometh 270d 💬 1
32
newShow HN: Glq LLM quantization using E8 latticegithub.com
▲ 2acd 126d discuss
33
newShow HN: Run HF Transformers in pure Go (10 MB binary, no Python)github.com
▲ 2openfluke 330d discuss
34
newAsk HN: Best LLM model for a RAG-based Android app across all smartphones?
▲ 1swaminarayan 186d 💬 1
35
newOff Grid: On-device AI-web browsing, tools, vision, image gen, voice – 3x faster
▲ 1ali_chherawalla 223d 💬 1
36
newFull LLM training and evaluation toolkitgithub.com
▲ 249testerui 680d 💬 6