8 GB accelerator memory
Q4 GGUF · text-first · llama.cpp
Use short context and text-only mode near the minimum.
Qwen
Text model
A smaller multimodal Qwen variant with fewer refusal behaviors.
Capabilities
The most useful reasons to choose this model, without making you read through its repository first.
Open-ended chat
Vision tasks
Tool calling
For providers
The provider requirements live here, separate from the information you need to choose and use the model.
8 GB accelerator memory
Q4 GGUF · text-first · llama.cpp
Use short context and text-only mode near the minimum.
12 GB accelerator memory
Q4 GGUF + projector · llama.cpp
The Q4 weights are 5.3 GB; vision adds a separate projector and long context adds KV cache.
Source and license
OpenMayhem links back to the source repository so you can inspect the model card, files, license, limitations, and creator guidance directly.
Uncensored edition by HauHau