GGUFs are here. Tutorials to run locally.
#1
by alanzhuly - opened
GGUFs are available: https://huggingface.co/NexaAI/Qwen3-VL-2B-Thinking-GGUF
Note currently only NexaSDK supports this model
Quickstart
- Download NexaSDK with one click
- one line of code to run in your terminal:
nexa infer NexaAI/Qwen3-VL-2B-Thinking-GGUF
The Nexa SDK is so convenient.
which generation parameters are the best?
the model is like not following me, if I ask it to take a note (tool call), it talks about grammar and shit.