AI skills and agents for developers

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

pentacoxian-dev · Kit

Runs Qwen3.8-27B with sparse attention on a single 24 GB GPU at a 262K-token context with image input, as GGUF files for people with a custom llama.cpp engine…

MiniCPM-V-4.7-1B-gguf

openbmb · Kit

Runs a 1B vision-language model through llama.cpp, answering text prompts about images. GGUF files in many quant sizes, for developers and hobbyists who want a…

MiniCPM-OCR Jev GGUF

openbmb · Kit

Scores OCR readings of text, formula and table regions with a quality value between 0 and 1, in GGUF files for llama.cpp. For people who check OCR results on t…

Hermes-3-Llama-3.2-3B

NousResearch · Kit

A 3.2B chat and assistant model that follows instructions, calls functions, writes structured output and code. For developers and hobbyists who run a model on…

Qwen3.5-0.8B-weight-space-programming-GGUF by NotCherry

NotCherry · Kit

Packages the Qwen3.5-0.8B weight-space-programming model as GGUF files for llama.cpp, with a 4-bit text model and a separate vision projector for image input.

Tess-4.5-27B GGUF

migtissera · Kit

GGUF builds of Tess-4.5, a 27B open-weights coding and agent model, for llama.cpp, with a vision projector and optional draft heads for faster generation. They…

Qwen3.6-35B-A3B lododo-Distill-v1.0 (GGUF)

lododoai · Kit

Runs as a local text model, a Qwen3.6-35B-A3B fine-tune trained on data written by Qwen3.8-27B and packed as one GGUF file for llama.cpp. For people who run mo…

Qwen3.8-27B-SLQ-GGUF

kaitchup · Kit

Compresses Qwen3.8-27B into three GGUF files with different size and fidelity levels, using a custom statistically lossless quantization. For people who run th…

K2-Horizon-7B-GGUF

IFM · Kit

Quantized GGUF copies of IFM's K2-Horizon-7B text model for running locally in llama.cpp, from BF16 down to 4-bit, with a 512K-token context window.

Qwen3.8-27B Intel Arc Tuned

Greatjedi · Kit

Runs a 27B Qwen3.8 model in GGUF files retuned for Intel Arc GPUs, with pure decode near 22 tokens a second in the author's tests. For people running llama.cpp…

Qwen3-Reranker-0.6B-Q8_0-GGUF

ggml-org · Kit

Ranks passages by relevance to a query, as an 8-bit GGUF copy of the Qwen3 0.6B reranker made with llama.cpp. For developers who want a small local reranker fo…

Laya-GGUF

ggml-org · Kit

Small 421M-parameter decision model in GGUF form that you serve locally and call through a systemone API. For developers who use llama.cpp tooling and want a c…

Kev-4B by ggml-org

ggml-org · Kit

Makes decisions through the /v1/systemone API of a llama server, from a GGUF copy of a 4.2B model. For developers who want a small local decision model.

gemma-4-E4B-it-GGUF by ggml-org

ggml-org · Kit

A GGUF-format copy of Google's gemma-4-E4B-it that you can run on your own computer with the Llama app or the llama serve command. For people who want Gemma ru…

gemma-4-12B-it GGUF

ggml-org · Kit

Runs Google's gemma-4-12B-it on your own computer as a GGUF file that ggml-org converted automatically, through the Llama app or the llama command. It suits pe…

DeepSeek-V4.1-Flash-1017 GGUF

ggml-org · Kit

GGUF files of DeepSeek's 748B V4.1 Flash 1017 model, converted by ggml-org with a vision file for images, for people with big-memory machines who run models th…

POCKET-35B-GGUF

FINAL-Bench · Kit

Runs a Korean-tuned 35B model on your own PC from GGUF files with llama.cpp, with a CPU-only path so no GPU is needed. For people who want a local language mod…

KVARK Sparkle 1.1 27B GGUF

Egzakta · Kit

Runs the 27B KVARK Sparkle 1.1 model from GGUF files in several sizes, with optional image input and speculative decoding. For people running models locally wi…

Kvark-Sparkle-1.0-27B-GGUF

Egzakta · Kit

GGUF files of KVARK Sparkle 1.0, a 27B vision-language model, for llama.cpp, Ollama and LM Studio, with the speculative-decoding head kept. For people running…

Maximizing Model Performance Guide

DavidAU · Kit

Guides you in tuning samplers and parameters for local language models, with steps for system prompts, reasoning models and expert settings in LM Studio, Silly…

Qwen3.8-27B iMatrix NVFP4 MTP GGUF

cdiamond · Kit

A 17.1 GB mixed-precision GGUF of Qwen3.8-27B that keeps its multi-token prediction layer, tuned for 256K context with vision on a 24 GB GPU. For people who ru…

Qwen3.6-35B-A3B MTP GGUF

byteshape · Kit

Runs Qwen3.6-35B-A3B from a GGUF quantization with Multi-Token Prediction for faster GPU decoding in llama.cpp. Made by ByteShape for people running local mode…

Meta-Llama-3.1-8B-Instruct-GGUF

bartowski · Kit

Quantized GGUF files of Meta's Llama 3.1 8B Instruct for local chat, such as 4.92 GB for Q4_K_M and 8.54 GB for Q8_0. Made by bartowski with an importance matr…

Llama-3.2-3B-Instruct-GGUF

bartowski · Kit

GGUF quantizations of Meta's Llama-3.2-3B-Instruct, made by bartowski with an importance matrix, from about 1.8 GB to 6.4 GB. For running a small chat model lo…

Forge-1-Gemma-4-E2B

YoSaNoo · Kit

A small coding-minded text model fine-tuned from Google's gemma-4-E2B and shared as GGUF files, so you can run it on your own laptop in Ollama, LM Studio, Unsl…

Spark-X2.6-1.7B-DSpark-GGUF

XHToken · Kit

A small draft model that speeds up Spark-X2.6-1.7B through speculative decoding, guessing up to seven tokens per step. For people who run that model locally on…

Llama-3.2-1B-Instruct-GGUF

unsloth · Kit

Chats, summarizes and answers questions in text on a laptop, as Unsloth's GGUF copy of Meta's small Llama 3.2 1B Instruct in precisions from 16-bit to 2-bit. F…

Qwen3-4B-GGUF

Qwen · Kit

A 4B chat model in GGUF format that runs locally in llama.cpp or ollama, with a thinking mode for reasoning and a plain mode for quick replies. Suits developer…

Qwen2.5-Coder-14B-Instruct-GGUF

Qwen · Kit

Gives you the Qwen2.5-Coder 14B instruct model as GGUF files in eight quantization sizes, for coding help with llama.cpp. For developers who want a stronger lo…

Qwen2.5-Coder-1.5B-Instruct-GGUF

Qwen · Kit

Gives you the small Qwen2.5-Coder 1.5B instruct model as GGUF files in eight quantization sizes, for coding help with llama.cpp on a laptop. For developers who…

Rein-NPC-4B

jmc0 · Kit

Drives game characters that hold a conversation, take in-game actions such as selling an item or calling guards, and stay in character under pressure. For game…

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

JetBrains · Kit

Runs JetBrains' 12B reasoning model locally in llama.cpp, Ollama or LM Studio, with five GGUF sizes to pick from. For developers who want a thinking model with…

Axion-1.0-35B-APEX-I-MiniPlus-V2.1-GGUF

IsValorum · Kit

Runs the 35B Axion-1.0 model locally in llama.cpp from one compressed GGUF file with mixed precision. A quantized release by IsValorum for people who want a la…

gpt-oss-20b-GGUF by ggml-org

ggml-org · Kit

Generates text on your own computer from a GGUF copy of OpenAI's gpt-oss-20b, packaged by ggml-org. For people who want to run an open 20B model locally in the…

Qwen3.8-27B-Ridge-GGUF

empero-ai · Kit

Runs Qwen3.8-27B as a compact 3.7 bits-per-weight GGUF file that suits a 16 GB GPU, with optional image input. For people running models locally with llama.cpp…

Qwen3.6-35B-A3B 2-bit GSQ GGUF

chtisgit · Kit

Runs a 35B Qwen model in a 2-bit GSQ GGUF conversion with a separate vision projector for llama.cpp. For people who want a large model in a small file on CPU o…

Qwen3.6-35B-A3B GGUF (ShapeLearn Quantized)

byteshape · Kit

Quantized GGUF versions of Qwen3.6-35B-A3B that read images and text, with CPU and GPU variants from about 9 GB, made with ByteShape's ShapeLearn. For develope…

Spark-X2.6-4B GGUF

bartowski · Kit

Small English and Chinese chat model as GGUF files from full bf16 down to about 2.4 GB, for llama.cpp, with a low or high thinking setting. For developers who…

Qwen3.6-35B-A3B-coding-reap50-GGUF

anik-jha · Kit

Writes code with Qwen3.6-35B-A3B cut to half its experts and packed as GGUF files for llama.cpp. Made for developers who want a coding model that fits in less…

Spark-X2.6-4B-DSpark-GGUF

XHToken · Kit

Speeds up text generation for Spark-X2.6-4B as a small draft model for speculative decoding, in GGUF format. Meant for people running that model locally with l…

DeepSeek-V4.1-Flash-1017-exl3

turboderp · Kit

Runs a compressed DeepSeek-V4.1-Flash-1017 in ExLlamaV3 at 1.68, 2.25 or 2.68 bits per weight. For people who run large models on their own hardware and want l…

Nanbeige4.3-33B-GGUF-UltraOptimised-Curated-Protium

SolsticeAI · Kit

Offers GGUF quantizations of the 33.1B Nanbeige4.3 model for llama.cpp and Ollama, with a reasoning protocol and up to 524,288 tokens of context. For developer…

Qwen2.5-1.5B-Instruct-GGUF

Qwen · Kit

Gives you the small Qwen2.5 1.5B chat model as GGUF files in eight quantization sizes, for running with llama.cpp on a laptop or modest GPU. For people who wan…

Ornith-1.5-35B-A3B-GSQ-RCO-GGUF

pfeifferj · Kit

Shrinks the Ornith-1.5-35B-A3B text model to 3-bit and 3.5-bit GGUF files, about 13 and 15 GB instead of 69 GB, for people who run local models with llama.cpp.

ttf-Qwen3.8-Flash-Next-GGUF

oguzeldereli · Kit

Runs Qwen3.8-Flash-Next, a 180B mixture-of-experts model squeezed to ternary weights, from one 40.4 GB GGUF file that is 4.6 times smaller than the FP8 release…

Hermes-3-Llama-3.1-8B-GGUF

NousResearch · Kit

Runs Hermes 3, an 8B general-purpose chat model from NousResearch, as a quantized GGUF file for llama.cpp. Suits people who want a local assistant with functio…

Hermes 3 Llama-3.1 8B

NousResearch · Kit

An 8B general-purpose chat model from Nous Research, built on Llama 3.1, with function calling, structured output, role play and code help. It suits developers…

Qwen3.8-27B-GGUF by bartowski

bartowski · Kit

A set of GGUF quantizations of Qwen3.8-27B by bartowski, from Q8_0 down to 3-bit, made with an importance matrix. For people running a 27B vision-language mode…

Jackrong_Qwopus3.8-27B-Coder-Flash-GGUF

bartowski · Kit

GGUF quantizations of Jackrong's Qwopus3.8-27B-Coder-Flash, made by bartowski with an importance matrix, in sizes from 17 GB to 55 GB. For running a 27B model…

Qwen3.5-9B-MTP-GGUF

unsloth · Kit

GGUF copies of Qwen3.5 9B that support multi-token-prediction speculative decoding in llama.cpp for faster generation. For people running the model locally who…