small-language-models repositories
Trending repositories tagged small-language-models, ranked by trending score. Updated daily.
-
1
jrz97619761/test-model-thing
A small proof-of-concept language model (not an LLM) that aims to incorporate latent-space prediction, internal state using recurrent trace units, and byte-by-byte output, built with MLX.
GitHub · Python · 328 stars · 60 forks · +15 stars in 24 hours · Trending score 1.98
-
2
baney75/smoothstone
A skill and CLI that lets small local models like LFM3-1.7B make 3D printable parts, from words or a picture, even through context compaction.
GitHub · Python · 81 stars · 6 forks · +6 stars in 24 hours · Trending score 0.98
-
3
OpenBMB/EC2-Bench
EC2-Bench (EC²-Bench): benchmark for edge-cloud collaboration in long-horizon LLM agents — task performance, resource usage & privacy exposure. arXiv 2610.17816
GitHub · Python · 24 stars · 0 forks · +2 stars in 24 hours · Trending score 0.81
-
4
ctrl-gaurav/effGen
[ICML 2026] effGen: Enabling Small Language Models as Capable Autonomous Agents
GitHub · Python · 210 stars · 35 forks · 0 stars in 24 hours · Trending score 0.61
-
5
shubham0204/SmolChat-Android
Running any GGUF SLMs/LLMs locally, on-device in Android
GitHub · Kotlin · 911 stars · 153 forks · 0 stars in 24 hours · Trending score 0.57
-
6
AuremHQ/weight-space-programming
wsp-kit by Aurem — an engineering tool for small models. Try to fix small open-weight models by editing weights directly, no retraining. An eval gate decides.
GitHub · Python · 18 stars · 2 forks · 0 stars in 24 hours · Trending score 0.26
-
7
palindrome-rl/AGENT8088
Open-Source Agentic Harness for Reliable Task Completion, even on small local models. 💻🧠🤖
GitHub · Python · 15 stars · 0 forks · 0 stars in 24 hours · Trending score 0.24
-
8
ankit-aglawe/tinyjev
A tiny jev-like model that answers Choice, Score and Noul questions in one forward pass and returns calibrated probabilities. MLX or PyTorch, fully offline, System One compatible.
GitHub · Python · 29 stars · 3 forks · 0 stars in 24 hours · Trending score 0.22
-
9
webis-de/small-text
Active Learning for Text Classification in Python
GitHub · Python · 646 stars · 80 forks · −1 stars in 24 hours · Trending score 0.22
-
10
Zihao-Wu06/distillops
Black-box LLM distillation for any verifiable task, with text or image inputs: teacher API -> rejection sampling -> SFT -> eval -> GRPO
GitHub · Python · 58 stars · 4 forks · −45 stars in 24 hours · Trending score 0.16
-
11
yogeshhk/FrugalAI
Evidence-first frugal AI: small language models and pipelines on an old laptop or Raspberry Pi, no cloud, no GPU. Measured benchmarks and recipes, with Indian-language focus.
GitHub · Python · 12 stars · 3 forks · 0 stars in 24 hours · Trending score 0.09
-
12
AlexanderNyr/AuraLite-AI
Train and fine-tune LLMs on an old PC without a GPU. AuraLite Studio (Windows app, no Python) picks a model for your computer, fine-tunes Qwen3.5 with LoRA/QLoRA on the CPU, trains small models from scratch and exports GGUF for Ollama and LM Studio. English and Russian UI.
GitHub · Python · 6 stars · 1 forks · 0 stars in 24 hours · Trending score 0.04
-
13
vaneeckhoutnicolas/quantum-cortex
A 27M parameter byte level language model with a memory outside its weights: a sealed journal of episodes it must cite or abstain from. Every claim has a row, a file and a test that can fail.
GitHub · Python · 5 stars · 0 forks · 0 stars in 24 hours · Trending score 0.03
-
14
Enoa-devteam/Stella_project
A cost-efficient, model-agnostic QQ-group AI agent built around an ~8K-token context window. Powered by NoneBot 2 + OneBot V11, it supports both local and online LLMs through a unified integration layer and extends its capabilities through compatibility with the AstrBot plugin ecosystem.
GitHub · Python · 9 stars · 3 forks · 0 stars in 24 hours · Trending score 0.03
-
15
Jewelzufo/granitepi-4-nano
Run IBM Granite 4.0 locally on Raspberry Pi 5 with Ollama.This is a privacy-first AI. Your data never leaves your device because it runs 100% locally. There are no cloud uploads and no third-party tracking.
GitHub · Shell · 12 stars · 2 forks · 0 stars in 24 hours · Trending score 0.00
-
16
masterFoad/NanoSage
Local LLM Powered Recursive Search & Smart Knowledge Explorer
GitHub · Python · 265 stars · 36 forks · 0 stars in 24 hours · Trending score 0.00
-
17
glukicov/laya_router
Model routing is a System 1 job: a 421M local decision engine (Laya) against a GPT-5 nano reasoning router. Same accuracy, 35x faster, free.
GitHub · Python · 13 stars · 6 forks · 0 stars in 24 hours · Trending score 0.00
-
18
LucianoDPerez/agent-devs
Open-source local coding agent designed to make Small Language Models (4B–35B) useful for real-world software development. AgentDevs maximizes small LLM capabilities through specialized tools, role-based agents, focused context, guardrails and objective verification.
GitHub · Python · 5 stars · 0 forks · 0 stars in 24 hours · Trending score 0.00
-
19
Kungie/gut
Judgment calls as one line of Python, built for TypeSafe AI's Jev and running on any small model: likely / classify / rate → YES, NO or UNSURE. Also local NLI, local LLMs, Ollama, vLLM, OpenAI.
GitHub · Python · 7 stars · 0 forks · 0 stars in 24 hours · Trending score 0.00
-
20
Mingbird/Mingbird-agent
Local-first agent harness (Windows + Ollama) for 2–9B models. Same 2B model: 0.017 → 0.821 across four agent harnesses — 48×. 288-cell benchmark, every cell public. One-click zero-outbound mode. 本地优先,一键断网,零遥测。鸣鸟
GitHub · Python · 21 stars · 1 forks · 0 stars in 24 hours · Trending score 0.00
-
21
kouhxp/gutsy
Local decision model with calibrated probabilities: send a state and yes/no, choice or score questions, get a probability for every option. 0.8B GGUF on CPU, Jev-style API.
GitHub · HTML · 76 stars · 4 forks · −7 stars in 24 hours · Trending score -0.01