Kits of AI agent skills, rules and prompts

Qwen3.8-27B-DFlash2-GGUF by z-lab

z-lab · Kit

A draft model in GGUF form that speeds up Qwen3.8-27B by proposing token blocks for the main model to verify. For people who run that model locally with llama.…

Clef-LoRA-for-Qwen3.8-27B-GGUF

trevest · Kit

Adds Cloudflare Clef's decision head to a Qwen3.8-27B chat model, so one llama.cpp server on a 24 GB GPU both answers typed questions and chats. It is a LoRA a…

Qwen3.8-27B-Longbook27-v2

summerAIO · Kit

Summarizes, answers questions about and continues book-length text with a fine-tuned 27B model that uses Gated DeltaNet layers, in English and Japanese. For pe…

Qwen3.8-27b-Terse-Coder-LoRA

Shockem · Kit

Cuts the length of Qwen3.8-27B's reasoning on coding tasks so answers arrive sooner, as a small LoRA adapter. For people who run the base model on their own ha…

Qwen3.8-27B-mixed-3.5bpw-MLX

rapid-mlx · Kit

A 27B vision-language model compressed to 3.5 bits per weight for Apple Silicon Macs with 24 GB of memory, served locally through Rapid-MLX. Suits Mac users an…

Qwen3.8-27B-NVFP4 by RadixArk

RadixArk · Kit

A pre-quantized NVFP4 copy of Qwen3.8-27B that reads text, images and video and answers in text, served with SGLang on NVIDIA Blackwell GPUs. Suits developers…

Qwen3.8-27B-QUASAR-NVFP4

QUASAR-QAT · Kit

Runs Qwen3.8-27B in 4-bit NVFP4 at 19.7 GB, trained with the QUASAR method to stay close to the full BF16 model. For people serving it with vLLM on an NVIDIA B…

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…

Qwen3.8-27B-MLX-8bit

lmstudio-community · Kit

Runs a 27B model that reads images and text in an 8-bit MLX build for Apple Silicon Macs. It suits people who want picture questions answered locally.

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…

Qwen3.8-27B-oQ4e-mtp

Jundot · Kit

Runs the 27B Qwen3.8 vision-language model on MLX in about 17.5 GB, reading text, images and video with a 262,144-token context. A mixed-precision quantization…

JDI-Decision-V0.9

JoyIndustrial · Kit

Answers multiple-choice style questions about images and text with option probabilities, using a Qwen3.8-27B decision system with built-in OCR. For developers…

Qwen3.8-27B-GSQ-RCO-IQ3_S-recovered-GGUF

Joakimpalm-Zen · Kit

Shrinks Qwen3.8-27B to a 3-bit IQ3_S GGUF with retrained scales. A research file for people who study quantization, not a faithful stand-in for the original mo…

Qwopus3.8-27B-Flash-GGUF

Jackrong · Kit

Cuts reasoning time and cost for long agent tasks, as a GGUF build of a Qwen3.8-27B fine-tune. Made for people who run agent loops on their own machine and wan…

Qwen3.8-27B-NVFP4 Deployment Edition

IteraCompute · Kit

Serves Qwen3.8-27B in NVFP4 on one RTX 5090 with vLLM, with a checksum-verified download, FP8 KV cache, tool calls and reasoning support. For developers self-h…

Kvark-Sparkle-1.0-27B

Egzakta · Kit

Reasons over images and text with fewer thinking tokens than its base Qwen3.8-27B, so answers arrive in about half the time at similar accuracy, per its card.…

Qwen3.8-27B Splash 8-bit

dmeight · Kit

Runs Qwen3.8-27B at 8-bit through the Splash runtime in LM Studio on Apple silicon. An unofficial package that keeps the model closer to the original than the…

Qwen3.8-Whittle-MoE-27B-MLX-4bit

barozp · Kit

A 4-bit MLX build for Apple Silicon of a mixture-of-experts model carved from the dense Qwen3.8-27B, with 17.8B active of 27B total parameters. For people who…

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…

Qwen3.8-27B-Quark-AWQ-MXFP4

amd · Kit

Runs Qwen3.8-27B as a smaller MXFP4-quantized copy made with AMD Quark and AWQ, served through vLLM. Made for developers who want a compressed 27B vision-langu…