How fast WollyMonjac/Tiny-2.1 is gaining stars, and where it lands on Trendshift and GitHub Trending
Activity and trending
Stars, forks and merged pull requests each day or month, lined up with the repository's rank on Trendshift Trending
Nov 15 – Nov 22, 2026
Stars +269in 8 days
050100
72
Forks +53in 8 days
01020
18
Merged PRs 0in 8 days
01
Trendshift Trendingwhere the repository ranked each day it made the top 25
Top 25 in C
228219
Nov 15Nov 16Nov 17Nov 18Nov 19Nov 20Nov 21Nov 22
The left and right arrow keys step from day to day; Home and End go to the first and the last
Stars, forks, merged pull requests and Trendshift Trending rank, by day
Day
Stars gained
Forks gained
Merged PRs
C
Sun, Nov 15, 2026
+0
+0
0
Not trending
Mon, Nov 16, 2026
+39
+18
0
#22
Tue, Nov 17, 2026
+72
+14
0
#8
Wed, Nov 18, 2026
+64
+7
0
#2
Thu, Nov 19, 2026
+43
+8
0
#19
Fri, Nov 20, 2026
+28
+6
0
Not trending
Sat, Nov 21, 2026
+17
+0
0
Not trending
Sun, Nov 22, 2026
+6
+0
0
Not trending
Total
+269
+53
0
1#1 on the list
7Rank that day
Not trending
Mentions and achievements
Where people are talking about WollyMonjac/Tiny-2.1, and every badge it has earned
1 post
TINY 2.1 has 367K parameters, ~380 KB of weights and needs ~540 KB of free conventional memory. Catch: trained on ~3,500 facts, it can confidently invent answers beyond them.
Someone fit a neural network on a floppy disk 😳 A developer built Tiny 2.1, a tiny model that runs even on DOS computers with an Intel 486 processor. Inside is a full mini-transformer with 367K…
Portable machine intelligence in BASIC: a QEMU-verified DOS/486 transformer and assistant runtime with fixed-point inference, hot-swappable local model packs, sharded recall indexes, and release bundles for legacy and constrained systems.
Z80-μLM is a 2-bit quantized language model small enough to run on an 8-bit Z80 processor. Train conversational models in Python, export them as CP/M .COM binaries, and chat with your vintage computer.