Kits of AI agent skills, rules and prompts

Qwen3.8-Flash-Next-GSQ-RCO-Coder-GGUF

ISTA-DASLab · Kit

A coding-focused GGUF build of Qwen3.8-Flash-Next with half its experts removed, cutting 354 GB at BF16 to 58.4 GB while keeping image input. For people with l…

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.…

Qwen3.8-Flash-Next-GSQ-RCO-GGUF

ISTA-DASLab · Kit

GGUF versions of Qwen3.8-Flash-Next at four sizes, with each tensor quantized at its own precision and a vision projector for image input. For people running a…

Qwenx86-4B (compact)

Quazim0t0 · Kit

Runs a calculator, Python and a C compiler inside its own weights, using 13 extra layers placed ahead of Qwen3.5-4B. For researchers and tinkerers who study mo…

S5-nano

maritaca-ai · Kit

Maritaca AI's small Portuguese and English model built on Qwen3.5-4B, with Think and Instruct modes and strong tool use, in BF16 for vLLM and SGLang. Suits dev…

Qwen3.8-27B-GSQ-RCO-GGUF

ISTA-DASLab · Kit

ISTA-DASLab's GGUF versions of Qwen3.8-27B in four sizes, each tensor quantized at its own precision, with a vision projector for images. Suits people who run…

qwen-concept-27b

ConceptCountry · Kit

Qwen3.8-27B with nine weight matrices edited by weight space programming, with no training, so it thinks with fewer tokens. An experimental release for researc…

Qwen3-TTS Demo by unclezhao

unclezhao · Kit

Runs a Qwen3-TTS text-to-speech demo in a Gradio page. The repository has no README text, so what the page offers is not described.

QwenScope

Qwen · Kit

Explore and steer the Qwen3.5-2B language model through sparse autoencoder features: compare two texts' feature activations, or push a feature into generation.…

Qwen3 TTS Voice Design

Qwen · Kit

A browser demo from the Qwen team for Qwen3 text-to-speech with voice design, as its name says. Suits creators and developers who want to try designing a voice…

KVPress Leaderboard

nvidia · Kit

Shows a leaderboard that benchmarks KV cache compression methods for language models, using Llama-3.1-8B-Instruct and Qwen3-8B. It suits researchers and engine…

Wasm Agents Blueprint

mozilla-ai · Kit

A static web page from mozilla-ai for testing AI agents powered by WebAssembly, naming the Devstral-Small-2507 and Qwen3-8B models. It suits developers explori…

Qwenputer Front Panel

jgalego · Kit

Replays recorded runs of Qwenputer, a Qwen3.5-4B model with a RISC-V CPU built into extra layers, beside a front panel of layers, registers and RAM. It runs in…

Qwen3 VL Demo

Qwen · Kit

A Gradio demo from the Qwen team for its Qwen3 VL vision-language family. Runs in your browser, or on your own computer with Python.

SAM3 + Qwen3.5

prithivMLmods · Kit

A browser demo of multi-object tracking that combines the SAM 3 model with a 2B Qwen3.5 model. Suits computer vision developers and researchers who want to try…

Saudi SALLM Q9B V1 Demo

Dr-Zeyad-Alghamdi · Kit

Runs a Gradio research demo of a private adapter on the Qwen3.5-9B language model from a browser page, for people who test models on GPU hardware.

Qwen3-TTS Demo

Qwen · Kit

Turns typed text into speech with the Qwen3-TTS models on a Gradio page, in the browser or on your own computer. For anyone who wants to hear the model's voice…

DSpine for Qwen3.8-27B

tencent · Kit

A five-layer draft model that guesses 16 tokens in parallel for Qwen3.8-27B, so the large model can check them together. Made for teams that serve that model.

Qwen3.8-27B

Qwen · Kit

Reads text, images and video and replies in text, with a 27B open model tuned for coding, research and multi-step agent work. Suits developers who run models t…