metadata
license: mit
base_model:
- moonshotai/Kimi-VL-A3B-Thinking-2506
pipeline_tag: image-text-to-text
tags:
- kimi-vl
GGUFs for moonshotai/Kimi-VL-A3B-Thinking-2506
Didn't see any GGUFs for this model, which is a legit model, so baked a couple. Hopefully useful to someone. Just straight llama-quantize off a BF16 convert_hf_to_gguf.py run. Sanity checked.
- Base model: moonshotai/Kimi-VL-A3B-Thinking-2506
- GGUFs for Instruct version: ssweens/Kimi-VL-A3B-Instruct-GGUF