mrbeniwal/TrueSkin-VL-2B

Quantization vs unsloth/Qwen2-VL-2B-Instruct-unsloth-bnb-4bit. unsloth/Qwen2-VL-2B-Instruct-unsloth-bnb-4bit is a quantized version of the other (BF16/U8).

1 derivatives checked

• mradermacher/TrueSkin-VL-2B-GGUF: Same weights, converted (fewer layers)

On the Hub · Downloads on Model Pulse