# WollyMonjac/Tiny-2.1 > A tiny question-answering transformer written in Turbo C 2.0 that runs under plain DOS on a 486DX or Pentium. It weighs 380 KB, fits on a floppy disk, and was trained on about 3,500 facts. - Magnitude: 4.2 out of 10 — Early signal - Stars: 328 total · +4 stars measured 2026-11-20, 00:09–03:39 UTC, ≈ 36 by evening - Star trust: star growth looks organic - Category: Language models · Language: Python · License: MIT · Created: 2026-11-15 · Last push: 2026-11-17 - GitHub: https://github.com/WollyMonjac/Tiny-2.1 · Page: https://gitnova.dev/en/r/WollyMonjac/Tiny-2.1 ## Useful for - Run a neural network on a retro PC under DOS without a modern OS - Rebuild TINY.EXE from source with TCC -ml TINY.C - Check how 8-bit weights fit into 540 KB of conventional memory ## Why it’s here - Star-counter measurements on 2026-11-20 (UTC), 00:09–03:39: 324 → 328 stars (+4). This is the change over that interval. - Estimated end-of-day forecast: about +36 stars, using observed gains and the previous day. - The repository is 5 days old and already has 328 stars. With less than two weeks of history, there's no usual pace to compare the spike against yet. - Top new repositories this week: #72. - About 8 forks a day — people are taking the code. - Recent forks include notable developers: @vic4key (344 followers), @bowei (221 followers). ## Star trust Star growth looks organic. Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer. ## Numbers - Forks: 47 - Issues and pull requests: 6 - Watchers: 4 - Average over the last week: 61 per day - Usual pace: too little history (under two weeks) - Stars in the last hour (measured): 1 ## Stars per day, last 6 days (oldest → newest, today is partial) 2026-11-15 … 2026-11-20: 51, 119, 61, 56, 41, 4 ## Magnitude by day, last 4 days 11-17 4.9, 11-18 4.8, 11-19 4.4, 11-20 4.2 ## Spotted in now - Top new repositories this week: #72 ## More in this category 1. **jingyaogong/minimind** — 7.4 · Breakout · Language models · Python · +196 stars measured 2026-11-20, 00:08–03:39 UTC, ≈ 696 by evening An open-source educational project for training a tiny 64M-parameter LLM (MiniMind) from scratch in PyTorch, covering the full pipeline: pretrain, SFT, LoRA, RLHF, RLAIF and Tool Use. Full card: https://gitnova.dev/en/r/jingyaogong/minimind.md 2. **openvinotoolkit/openvino** — 6.3 · Breakout · Language models · C++ · +39 stars measured 2026-11-20, 00:08–03:39 UTC, ≈ 201 by evening OpenVINO is an open-source toolkit for optimizing and deploying deep learning model inference on Intel CPU, GPU and NPU. It supports models from PyTorch, TensorFlow, ONNX, Keras, PaddlePaddle, JAX/Flax and Hugging Face with C++, Python, C… Full card: https://gitnova.dev/en/r/openvinotoolkit/openvino.md 3. **asgeirtj/system_prompts_leaks** — 6.0 · Breakout · Language models · Python · +82 stars measured 2026-11-20, 00:09–03:39 UTC, ≈ 370 by evening A collection of extracted system prompts from Anthropic, OpenAI, Google, xAI and others — the hidden instructions chatbots receive before a user's first message. Full card: https://gitnova.dev/en/r/asgeirtj/system_prompts_leaks.md 4. **sybil-solutions/inference-optimisation-skill** — 4.3 · Cooling · Language models · Python · +11 stars measured 2026-11-20, 00:09–03:39 UTC, ≈ 94 by evening Agent skill for hill-climbing the speed of a local LLM server: decode, speculative decoding, prefill, KV cache, startup and TTFT on any hardware and quantization. Full card: https://gitnova.dev/en/r/sybil-solutions/inference-optimisation-skill.md 5. **microsoft/BitNet** — 4.2 · Breakout · Language models · C++ · +16 stars measured 2026-11-20, 00:09–03:39 UTC, ≈ 139 by evening Official inference framework for 1-bit LLMs (BitNet b1.58) with optimized kernels for CPU and GPU. Runs ternary models fast and losslessly, including a 100B model on a single CPU. Full card: https://gitnova.dev/en/r/microsoft/BitNet.md --- Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score. Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast. Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself. Data as of 2026-11-20 03:48 UTC, updated every 30 minutes.