Paradee-8M v1.0
sahilmahendrakar · Kit
Speaks English text in a single voice with an 8M-parameter model distilled from Kokoro-82M. The int8 ONNX file is about 9 MB and runs on a CPU. Suits developer…
New
AI projects from Hugging Face
Categories and filters
Listings
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…
New
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…
New
Kandinsky S2V 1.0 Lite distilled
kandinskylab · Kit
Turns one reference image and a speech recording into an avatar video, animating the whole figure to match the speech. The distilled Lite version runs 16 steps…
New
Qwen3.5-4B-Claude-4.6-Opus-Reasoning-Distilled-GGUF
Jackrong · Kit
Thinks through problems step by step inside think tags, as a 4B Qwen3.5 model fine-tuned on reasoning chains and packaged as GGUF. For people who run a small r…
New
Runs a tiny 0.8B reasoning-tuned chat model in the MLX format at 6-bit, converted from Jackrong's Qwen3.5 distilled model. For people who want a tiny local mod…
New
Qwen3.6-35B-A3B-Claude-4.6-Opus-Reasoning-Distilled-GGUF
hesamation · Kit
Runs a reasoning-tuned Qwen3.6-35B-A3B on your own machine as GGUF files in four quant sizes, trained on Claude Opus 4.6 style reasoning data. For people who w…
New
Z-Image-Turbo-GGUF by unsloth
unsloth · Kit
Unsloth's GGUF files of Z-Image-Turbo, a fast distilled text-to-image model that the authors say fits on a 16 GB consumer GPU. For people who generate images l…
New
Qwen3.8-27B-Fable-5-Coding-Distilled
khazarai · Kit
Debugs and reviews code by checking real files before it proposes a fix, a Qwen3.8-27B fine-tune trained on 195M tokens of reasoning traces. For developers who…
New
DistilBERT base uncased
distilbert · Kit
A small, fast English language model distilled from BERT base, with 67M parameters. Fills in masked words and is mainly meant to be fine-tuned for classificati…
New
Hy-Nomas x LTX-2.5 Audio Workflows
BennyDaBall · Kit
Two ComfyUI workflows that add a soundtrack to silent Hy-Nomas video worlds or any clip, using the stock LTX-2.5 distilled model while the picture stays untouc…
New
Paradee-8M v1.3
sahilmahendrakar · Kit
A tiny 7.88M-parameter text to speech model with eight voices in English, Hindi, French and Spanish, distilled from Kokoro-82M, for developers who need fast sp…
New
Z-Image
Tongyi-MAI · Kit
Generates images from a text description with a 6.2B-parameter model, the full undistilled base of the Z-Image family. Built for creators, researchers and deve…
New
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…
New
Qwen3.8-9B-Distill-GGUF
empero-ai · Kit
GGUF quantizations of Empero's Qwen3.8-9B, a reasoning model distilled from a larger Qwen3.8 into the Qwen3.5-9B design, for llama.cpp, Ollama, LM Studio and s…
New
Idol Turbo by speridlabs
speridlabs · Kit
Turns one picture of an object into up to a million 3D Gaussians in 5 guidance-free steps, as a distilled and faster version of Idol. For 3D artists and ComfyU…
New
Muse Glimmer 30B
meta-models · Kit
Reads text and images and carries out agent tasks such as tool calls and multi-step reasoning on a local machine, in a 30B model distilled from Muse Spark. For…
New
moss_image_base_dmd2
data-archetype · Kit
Makes images from text in 8 steps instead of 50, as a distilled LoRA for the MOSS-Image-Base model. For ComfyUI and Diffusers users who want faster image gener…
New
Teacher in the Loop
MithrilMan · Kit
Runs small 8M-parameter text-to-speech voices distilled from Kokoro-82M entirely in your browser, with audio samples that compare the training recipes.
New
SILVA Aesthetic Scorer
Jannchie · Kit
Scores an uploaded illustration three ways, with one person's taste and two distilled AI judges, each as a number from 0 to 1. Suits artists, dataset curators…
New