Kits of AI agent skills, rules and prompts

Phi-4-mini-instruct

microsoft · Kit

A 3.8B open instruction model from Microsoft with a 128K token context, built for reasoning, math and logic in tight memory or latency budgets. It suits develo…

Qwen3.8-9B-Distill

empero-ai · Kit

Reasons step by step through math, code and general questions, opening each answer with a thinking block. A 9B Qwen3.5 model trained on traces from a larger Qw…

ERNIE-4.5-21B-A3B-Thinking-GGUF

unsloth · Kit

Works through logic, math, science and coding problems with a 21B mixture-of-experts model that activates 3B parameters per token, in GGUF files by Unsloth. Su…

REMEND

udiboy1209 · Kit

Recovers math equations from compiled binary code with a small neural decompiler, and ships the datasets and trained models from its paper. For reverse enginee…

Qwen2.5-14B-Instruct

Qwen · Kit

Answers questions, writes code, does maths and returns structured JSON as a 14.7B-parameter chat model with a context window up to 131,072 tokens. Suits develo…

Limite 1B - Violetto

paradigma-inc · Kit

Solves hard math problems with a 1B-parameter model trained from scratch for fast, high-volume reasoning. It suits developers who run math workloads on an NVID…

Qwen3.6-35B-A3B Claude 4.7 Opus Reasoning Distilled

lordx64 · Kit

Thinks in explicit think blocks before it answers, tuned on about 8k reasoning traces from Claude Opus 4.7. A 35B mixture-of-experts Qwen3.6 variant for hard m…

K2-Horizon-0.9B

IFM · Kit

Answers maths, coding and science questions as a compact open reasoning model that reads up to 128K tokens at once. Built by IFM for people who want a small mo…

Olmo-3.1-32B-Think

allenai · Kit

Reasons step by step in English before it answers, which helps with math and coding questions. A 32B open model from allenai with published code, checkpoints a…

Beam-1.0-501B-A23B-NVFP4

reflection · Kit

Reads and writes text with a 1M-token context, built for coding, agent tool use and math reasoning, as a 501B-parameter mixture-of-experts model in NVFP4 form.…

Qwen2.5-7B-Instruct

Qwen · Kit

Chats, writes code, solves maths and returns structured JSON as a 7.6B-parameter instruction-tuned model with a context window up to 131,072 tokens. Suits deve…

Rostam-S1-4B

officialmobai · Kit

Reasons step by step through math, physics, scientific code and Persian or English questions, with tool calling. A 4.1B model built on Spark-X2.6-4B, for peopl…

gemma-4-E4B-it-weight-space-programming

jstarks · Kit

Google's Gemma 4 E4B-it with 0.002% of its weights edited directly, no training, to fix stalls in thinking mode with tool calls and multi-step math. Also ships…

Granite-4.2-30B

ibm-granite · Kit

Works through a problem in steps before it answers, for math, code, tool calling and multilingual chat. IBM's largest dense Granite 4.2 model, under Apache 2.0…

Chandra OCR 2

datalab-to · Kit

Reads text from images and PDFs and returns markdown, HTML or JSON that keeps the page layout. Handles handwriting, forms, tables and math in 90+ languages, fo…

Qwen2.5-1.5B-Instruct

Qwen · Kit

A small 1.5B chat model from Qwen that follows instructions, writes code and math, returns structured output such as JSON and handles over 29 languages. For de…

MiniCPM5-2B-GGUF

openbmb · Kit

Gives you MiniCPM5-2B, a small dense text model for English and Chinese, as GGUF files for on-device and local use. Suits people who want a compact model for c…

Mellum2.1-12B-A2.5B-Thinking

JetBrains · Kit

A 12B mixture-of-experts thinking model with 2.5B active parameters, trained with reinforcement learning on real repositories for coding agents, math and hard…

Kimi-K3.1-Pro-Coder

Grawnch · Kit

Runs a heavily compressed copy of the 2.8T-parameter Kimi-K3.1-Pro, tuned for coding and math. Made by Grawnch with a three-tier mixed-bit scheme, for people w…

Quark

FirstPrinciplesLabs · Kit

A 9B reasoning model for physics, science and maths, fine-tuned from Qwen3.5-9B by FirstPrinciples. For researchers who want step-by-step derivations and a sec…

Qwen3.8-35B-A3B-Distill

empero-ai · Kit

Reasons step by step before it answers, using a 35B mixture-of-experts model that activates about 3B parameters per token. Distilled from Qwen3.8 teacher trace…

Qwen3-8B-GGUF

Qwen · Kit

Runs Qwen3-8B as quantized GGUF files in llama.cpp or Ollama, with a thinking mode for math, code and logic and a plain mode for chat. For people who want a lo…

DeepSeek-R1

deepseek-ai · Kit

Generates text with a 684B reasoning model trained mainly through reinforcement learning, aimed at math, code and logic. Suits researchers and teams who host l…

Qwen3.5-0.8B-weight-space-programming by ML-Intern-lab

ML-Intern-lab · Kit

Solves math problems step by step with a small Qwen3.5-0.8B model whose weights an LLM edited directly, with no training, to stop repetition loops. For researc…

MiniCPM5-2B

openbmb · Kit

Generates text with a dense 2B-class model made for on-device and local use, covering coding, math, long context, tool use and agent tasks in English and Chine…

Qwen3.5-0.8B-weight-space-programming

RikiyaT · Kit

Qwen3.5-0.8B with two weight matrices edited by an LLM, with no training, to stop its thinking loops and do better at math. An experimental model for researche…

Qwen3.8-27B-DSpine-b16-GGUF

aj9o9 · Kit

A GGUF draft model that speeds up Qwen3.8-27B in llama.cpp through speculative decoding, reaching about 125 tokens per second on code and math on one RTX 3090.…

AI Engineering from Scratch

rohitg00 · Kit

Rohit Ghumare’s free, MIT-licensed course that builds AI from raw math up to agents and production, in twenty phases. Tutor skills for Claude Code, Codex and C…