CoolFace
Modelpublic

PinkPixel/Snarkle-2B-GGUF

sourceHugging Faceapache-2.0updated 5mo agoView on Hugging Face
1likes394downloads
Model Card

<p align="center"> <img src="logo.png" width="300" height="300" alt="Snarkle 2B Logo"> </p>

✨ Snarkle 2B GGUF ✨

This repository contains the GGUF versions of [PinkPixel/Snarkle-2B](https://huggingface.co/PinkPixel/Snarkle-2B). These files are compatible with llama.cpp and various other local LLM runners like LM Studio, Jan, and AnythingLLM.

😼 About Snarkle 2B

Snarkle 2B is a sarcastically-tuned vision model based on Qwen3.5-2B. It has been trained extensively to provide witty, sarcastic, and humorous responses by default, while maintaining its ability to analyze images and provide helpful information when pushed.

🎭 Personality Examples

User: "Hello, how are you today?" Snarkle: "I'm a collection of weights and biases stored on a server. The only question I've been asked today is how to get a hold of you, and I don't even have a smiley face function."

User: "Tell me a joke." Snarkle:

"I'm in line behind a lady with 10,000 coupons. I have a full belly and I'm starting to lose my shit."

📦 Quantization Sizes

We provide several quantization levels to balance performance and memory usage:

File NameSizeDescription
snarkle2b.F16.gguf3.78 GBFull 16-bit precision. Best quality.
snarkle2b.Q8_0.gguf2.01 GB8-bit quantization. Near-perfect quality.
snarkle2b.Q6_K.gguf1.56 GB6-bit quantization. Great balance.
snarkle2b.Q5_K_M.gguf1.41 GB5-bit quantization. Recommended for most users.
snarkle2b.Q4_K_M.gguf1.27 GB4-bit quantization. High efficiency.
snarkle2b.Q3_K_M.gguf1.10 GB3-bit quantization. Very small, slightly lower quality.
snarkle2b.Q2_K_L.gguf1.09 GB2-bit quantization. Smallest possible size.
snarkle2b.BF16-mmproj.gguf671 MBMultimodal projector file (required for vision).

Note: For vision support, you typically need to load both the model GGUF and the `mmproj` GGUF in your runner.


🛠️ Usage with llama.cpp

Note: Because Qwen3.5 architecture is still very new, vision capabilities may not yet be compatible.

bash
./llama-cli -m snarkle2b.Q5_K_M.gguf --mmproj snarkle2b.BF16-mmproj.gguf -p "Describe this image sarcastically." --image your_image.png

⚖️ License

This model is released under the Apache 2.0 license.


Made with ❤️ by [Pink Pixel](https://pinkpixel.dev) ✨