AI skills and agents for developers

mmBERT-base

jhu-clsp · Kit

Reads and encodes text in over 1,800 languages, for classification, embeddings, retrieval and fill-in-the-blank tasks. Built for developers and researchers who…

Primal VAE

ostris · Kit

Provides small image autoencoders that compress pictures to one or two latent channels and need no scaling factor, then patch up to match the Flux or Stable Di…

ClipProj-MiniMax-H3

NicoLab28 · Kit

Lets a small Qwen3-VL stand in for the 32B text encoder of MiniMax H3 in ComfyUI, cutting VRAM from 15.7 GB to 4.5 GB. A proof of concept that needs a custom n…

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…

SPEAR XLarge v2

marcoyang · Kit

Turns 16 kHz speech and general audio into 1280-number frame-level features, as a pretrained Zipformer encoder with about 600M parameters. For researchers who…

LightVAE

lightx2v · Kit

Swaps in lighter video autoencoder parts for Wan2.1, Wan2.2 and MiniMax-H3, through a ComfyUI node or a Python script. For video AI users who want compact VAE…

Qwen3.8-27B-oQ8e-mtp

Jundot · Kit

Runs Qwen3.8-27B as an 8-bit mixed-precision MLX checkpoint with its vision encoder and MTP head, for image and text chat on Apple hardware. For people who wan…

GLM-5.3-Flash-oQ4e-mtp

Jundot · Kit

A mixed-precision MLX copy of zai-org's GLM-5.3-Flash multimodal mixture-of-experts model, about 4.6 bits per weight, with the vision encoder and multi-token p…

MoEViE-L16-384

facebook · Kit

A Mixture-of-Experts vision encoder from Meta that matches images to text labels with no extra training, here the L/16 model at 384px. Licensed for non-commerc…

ARK-ASR-3B

Edge0 · Kit

Turns speech into text in many languages, with a Whisper-style audio encoder feeding a Qwen decoder. For developers and researchers who want multilingual trans…

t5-v1_1-xxl-encoder-gguf

city96 · Kit

A GGUF conversion of Google's T5 v1.1 XXL text encoder, for turning text into embeddings in llama.cpp or feeding image generation models through ComfyUI-GGUF.…

MOSS-Image-SFT GGUF

axiomofmind · Kit

Unofficial GGUF files of the MOSS-Image-SFT diffusion transformer in Q8_0 and Q4_K_S, for running text-to-image locally with stable-diffusion.cpp. Needs a sepa…

ModernBERT-large

answerdotai · Kit

Predicts a hidden word in English text or code, and after fine-tuning serves as a larger long-context encoder for search, classification and retrieval. Made fo…

ModernBERT-base

answerdotai · Kit

Predicts a hidden word in English text or code, and after fine-tuning serves as a long-context encoder for search, classification and retrieval. Made for devel…

VieGem-ASR

5CD-AI · Kit

Transcribes Vietnamese and mixed Vietnamese and English speech, offline or in 0.48 second streaming chunks, with a 359M-parameter model on Google's EmbeddingGe…

TAEF2

madebyollin · Kit

Previews FLUX.2 image generation in real time with a tiny autoencoder that shares the FLUX.2 VAE's latent format. For image app developers and people with limi…

Qwen3.8-27B-oQ6e-mtp

Jundot · Kit

A mixed-precision MLX copy of Qwen3.8-27B at about 6.9 bits per weight, with the vision encoder and multi-token prediction head included, for running locally o…

Qwen3.6-35B-A3B-oQ6e-mtp

Jundot · Kit

A mixed-precision MLX copy of Qwen3.6-35B-A3B at about 6.8 bits per weight, with the vision encoder and multi-token prediction head included, for running local…

V-JEPA 2

facebook · Kit

Turns videos and images into embeddings for video classification, retrieval, or as the video encoder of a vision-language model. Built by FAIR at Meta for deve…

CLM-v0.1-8B

Contrastive-LM · Kit

Scores candidate answers, actions or tool names for a given state with a probability each, instead of writing text. A fast decision model on a frozen Qwen3-8B…

DeepSeek V4.1 Flash GGUF for DwarfStar

antirez · Kit

Gives Mac users calibrated 2-bit and 4-bit GGUF files of DeepSeek V4.1 Flash, plus a separate vision encoder, for DwarfStar's Metal engine with SSD streaming.…

sd-vae-ft-mse-original

stabilityai · Kit

Replaces the autoencoder in Stable Diffusion with a fine-tuned decoder that reconstructs images, especially faces, more smoothly. Suits people running the orig…

Qwen3.8-27B-Splash

incoai · Kit

Serves Qwen3.8-27B on Apple silicon Macs through Inco AI's Splash engine, with a 4-bit model, a DFlash 2 draft and a vision encoder in one package. Works only…

UltraBERT-380M

dmis-lab · Kit

Predicts masked words in English text and gives you a pre-trained encoder with a 32K context to fine-tune for classification or retrieval. A fill-mask model fr…

Qwen3-VL for ComfyUI

Comfy-Org · Kit

Repackaged Qwen3-VL 4B and 8B model files for ComfyUI's text encoder folder, offered in several precisions from bf16 to 4-bit styles. For ComfyUI users who nee…

FLUX.2 Klein 4B for ComfyUI

Comfy-Org · Kit

Repackaged FLUX.2 Klein 4B model files for ComfyUI that turn a text prompt into an image. Includes diffusion models, text encoders and a VAE, with a ready text…

ACE-Step 1.5 by Comfy-Org

Comfy-Org · Kit

Model files for generating music from text in ComfyUI, repackaged from the original ACE-Step 1.5 release. Includes checkpoint, diffusion, text encoder and VAE…

flux_text_encoders

comfyanonymous · Kit

Supplies text encoder checkpoints for Flux image models, made for ComfyUI's DualClipLoader node. For ComfyUI users who run Flux on their own machine.

Qwen3.5-27B

Qwen · Kit

Reads text and images and writes text, as a 27B Qwen model with a vision encoder and a 262,144-token native context. For developers who build assistants and ag…

Qwen3.5 for ComfyUI

Comfy-Org · Kit

Repackaged Qwen3.5 2B, 4B and 9B model files for ComfyUI's text encoder folder, in bf16 and two quantized styles for the 9B size. For ComfyUI users who need a…

Llama-V-JEPA-LM-Qwen3-4B

kkt94 · Kit

Answers questions about video clips with a 5.1B model that joins a frozen V-JEPA 2.1 video encoder to Qwen3-4B-Instruct-2507, for people who need video underst…

Llama-V-JEPA-LM-Qwen3-1.7B

kkt94 · Kit

Answers questions about video clips with a 2B model that joins a frozen V-JEPA 2.1 video encoder to Qwen3-1.7B, for people who need video understanding on one…

Llama-V-JEPA-LM-Llama3.2-3B

kkt94 · Kit

Answers questions about video clips with a 4.2B model that joins a frozen V-JEPA 2.1 video encoder to Llama-3.2-3B-Instruct, for people who need video understa…

Llama-V-JEPA-LM-Llama3.2-1B

kkt94 · Kit

Answers questions about video clips with a small 1.5B model that joins a frozen V-JEPA 2.1 video encoder to Llama-3.2-1B-Instruct, for people who need video un…

Llama-V-JEPA-LM-Llama3.1-8B

kkt94 · Kit

Answers questions about video clips by joining a frozen V-JEPA 2.1 video encoder to Llama-3.1-8B-Instruct, made for people working on video understanding.

Llama-V-JEPA-LM-Qwen3-8B

kkt94 · Kit

Answers questions about video clips with a 9.2B model that joins a frozen V-JEPA 2.1 video encoder to Qwen3-8B, for people who need video understanding on a GP…

Qwen3.5-9B-Base

Qwen · Kit

Gives researchers and developers a pre-trained 9B base model with a vision encoder, meant for fine-tuning and experiments rather than direct chat. Handles text…

gemma-4-12B

google · Kit

Google's Gemma 4 12B Unified model, an open model that reads text, images, audio and video and writes text, with a 256K context and no separate encoders. For d…

WeVisOne-VL

Comfy-Org · Kit

Packs Tencent's WeVisOne-VL model files for ComfyUI, in 4B and 2B sizes with BF16 and int8 versions. For ComfyUI users who need the files in their text encoder…

Vela 3.0 · Studio

vllm-sr · Kit

Answers questions about an image or a text with a small 0.25B encoder running on CPU: point at an object, extract fields, catch OCR mistakes or decide between…

MuseTalkDemo

TMElyralab · Kit

A Docker-packaged demo app from TMElyralab for its MuseTalk model, bundled with DWPose, a Stable Diffusion autoencoder and ffmpeg tooling. It suits developers…