needle-2-esp32

A 45M-parameter LLM: needle 2 running fully offline on an ESP32-S3, turning plain-English requests into guaranteed-valid JSON tool calls.

andrisgauracs/needle-2-esp32

View on GitHub ↗

A 45M-parameter LLM: needle 2 running fully offline on an ESP32-S3, turning plain-English requests into guaranteed-valid JSON tool calls.

needle-2-esp32 grew +5.4% in the last 30 days, ranks 115th of 177 in Web / Edge / On-Device Runtime, last commit 96 days ago.

Star trajectory

82 days tracked
2026-08-31213 stars today2026-11-22
Momentum

+5.4% in 30d, above the Web / Edge / On-Device Runtime median of +1.8%.

Maintenance

Last commit 96 days ago, staler than the median of 6d.

How it compares in Web / Edge / On-Device Runtime

needle-2-esp32
213
stars
+5.4% 30d
commit 96 days ago
Web / Edge / On-Device Runtime median
311
stars
+1.8% 30d
commit ~6d ago
Leader · mlc-llm
23.4k
stars
+0.8% 30d
commit today

Ranked 115th of 177 by stars.

Ranked by shared tags, then keywords, then stars
  1. Run LLMs on AMD Ryzen™ AI NPUs in minutes; purpose-built and deeply optimized for the AMD NPUs.

    +97 (+4.9%) in 30d · Committed today · C++ · Other license

    Shares Web / Edge / On-Device Runtime, Inference Optimization

  2. NobodyWho is an inference engine that lets you run LLMs locally and efficiently on any device.

    +83 (+5.1%) in 30d · Committed 2d ago · Rust · EUPL-1.2

    Shares Web / Edge / On-Device Runtime, Inference Optimization

  3. Run MoE models bigger than your RAM. Frontier-size MoE on a phone, laptop, edge. Lossless, on stock llama.cpp…

    +425 (+65%) in 30d · Committed today · C++ · Apache-2.0

    Shares Web / Edge / On-Device Runtime, Inference Optimization

  4. llama.cpp on a jailbroken PS5: run any GGUF model natively on the console, starting with Qwen 3.8

    +231 (+36%) in 30d · Committed 3d ago · C++ · GPL-3.0

    Shares Web / Edge / On-Device Runtime, Inference Optimization

  5. CPU inference for the DeepSeek family of large language models in C++

    +2 (+0.6%) in 30d · Committed 415d ago · C++ · Other license

    Shares Inference Optimization, Web / Edge / On-Device Runtime

  6. 7-node ESP32-S3 cluster running a 0.4B LLM via 1.58-bit (BitNet) ternary quantization over SPI daisy-chain

    +14 (+5.6%) in 30d · Committed 45d ago · C++ · MIT

    Shares Web / Edge / On-Device Runtime, Inference Optimization

  7. GenAI & agent toolkit for Apple Silicon Mac, implementing JSON schema-steered structured output (3SO) and…

    +0 (+0.0%) in 30d · Committed 267d ago · Python

    Shares Web / Edge / On-Device Runtime, Inference Optimization

  8. Gemma 4 26B-A4B inference in ~2 GB of RAM on any M-series MacBook

    +442 (+6.3%) in 30d · Committed 7d ago · Swift · Apache-2.0

    Shares Web / Edge / On-Device Runtime, Inference Optimization

  9. 2bit quants, kernels and runtime for consumer devices.

    Committed 16d ago · C++ · Other license

    Shares Web / Edge / On-Device Runtime, Inference Optimization

  10. Run Mixtral-8x7B models in Colab or consumer desktops

    -3 (-0.1%) in 30d · Committed 957d ago · Python · MIT

    Shares Inference Optimization, Web / Edge / On-Device Runtime

Language
C
License
Apache License 2.0
Contributors
1
Forks
33
Watchers
2
Open issues
1
Releases
0
Created
2026-08-13
Stars this week
+2

You've seen where needle-2-esp32 stands today.

Get the moves before everyone else: the 5 Web / Edge / On-Device Runtime repos climbing fastest, every Tuesday.

Free weekly digest. Double opt-in, unsubscribe anytime.

Maintain needle-2-esp32?

Claim this page to add your own call-to-action.

Claim this page