Kits of AI agent skills, rules and prompts

AstrLink Guard

QuantumNous · Kit

Finds personal information and credentials in Chinese, English and mixed text, code, logs and AI coding assistant requests, locally in ONNX. For developers who…

Qwen3.8-Flash-Next-DFlash2-GGUF

nazeshinjite · Kit

GGUF draft model that speeds up Qwen3.8-Flash-Next in llama.cpp through speculative decoding, in 334 MiB and 622 MiB files. It is not a standalone model, and i…

Nanbeige4.3-33B-INT4

Nanbeige · Kit

INT4 quantized version of Nanbeige4.3-33B, a 33B model for coding and professional agent tasks, made with quantization-aware training. For developers who want…

Nanbeige4.2-3B by Nanbeige

Nanbeige · Kit

Compact looped-transformer model of 4.2B parameters for agent work such as tool use, office tasks and coding, in English and Chinese. For developers who want a…

Qwen3.8-27B Fable-5 Coding Distilled GGUF

mradermacher · Kit

GGUF quantized files of a 27.3B coding-distilled Qwen3.8 model, from 2-bit to 8-bit with an optional multi-modal supplement. They suit developers who run a cod…

flint-mixed-3-4bit

mlx-community · Kit

A community MLX build of Recursive's 40B Flint coding model that shrinks the experts to 3 bits, so it fits a 24 GB or 32 GB Apple Silicon Mac. Made for develop…

Muse Glimmer 30B GGUF by meta-models

meta-models · Kit

GGUF builds of a 30-billion-parameter agentic model for llama.cpp, with an optional image encoder and a speculative decoding drafter. They suit people who run…

DeepSeek-V4.1-Flash-1017-GSQ-agentic-strata

kaushikvira · Kit

Runs the 763.2B-parameter DeepSeek V4.1 Flash as a 153 GiB mixed-precision build tuned for agentic and coding work on the strata engine. For people with a larg…

Qwen3.8-Flash-Coder APEX-I-MiniPlus V2.1 GGUF

IsValorum · Kit

An English-only coding model in GGUF, a 42.6B mixture-of-experts quant of about 21.8 GB, for code completion, refactoring and agentic tool calls in llama.cpp o…

Qwen3.6-35B-A3B-2Bit-GSQ

ISTA-DASLab · Kit

A 2-bit quantized copy of Qwen3.6-35B-A3B made with GSQ, a Gumbel-Softmax method, that keeps most reasoning and coding ability at a much smaller memory footpri…

Flint-DFlash2

incoai · Kit

A 403M-parameter draft model that speeds up serving of the Flint language model with speculative decoding in SGLang, without changing its output. It is not a s…

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…

Parallel Constrained Decoding for Apple Silicon

harshatheg · Kit

Extracts structured fields, routes decisions and classifies text on Apple Silicon with MLX, scoring every schema field at once. Cuts latency 5.6x to 7.0x on an…

North Mini Code

CohereLabs · Kit

An open-weights research model from Cohere for writing code, agentic software engineering and terminal tasks. A 30B model with 3B active, 256K context. For dev…

North-Mini-Code-1.0 GGUF

byteshape · Kit

GGUF copies of the North-Mini-Code-1.0 coding model, compressed with ByteShape's ShapeLearn for GPU use in llama.cpp. Four sizes from 12.1 GB to 21.5 GB, for d…

Qwen3.8-27B-NVFP4-DGX-SPARK

autotrust · Kit

Speeds up Qwen3.8-27B NVFP4 decoding about 3.9 times on a DGX Spark, using the same weights and a tuned speculative-decoding setup. For teams serving it with v…

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…

DSpine

tencent · Kit

Drafts several tokens at once for speculative decoding with Qwen3-8B, so a model server can check them in one pass. For inference engineers and speculative dec…

K2-Horizon-3.7B

IFM · Kit

Handles coding, reasoning and agent-style tasks as a small open model with a 512K token context window. Built by IFM for people who want public training data,…

Tessera-27B-B-CJK-RL

ZelligeAI · Kit

Runs coding-agent loops with a 27B model that thinks in a compressed English and Chinese shorthand, so it spends fewer thinking tokens per turn. For developers…