Models

4 models

dlasher/Qwen3-VL-30B-A3B-Instruct-ENG

pulled as BF16, vocab slice (combined_en_huge) requant to IQ4_NL (combined_en_huge) -- (English + Coding focus) - ~20% faster than Q4_K_M

vision

9
dlasher/Qwen3-VL-30B-A3B-Instruct

full BF16 model, hand-requant to IQ4_NL, with combined_en_huge dataset (English + Coding focus)

vision

20
theoistic/Qwen-3-VL-30B-A3B-Instruct

High Quality Vision Instruct Model

vision

630
mirage335/Qwen-3-VL-30B-A3B-Instruct-virtuoso

Recommended for transcribing and summarizing text from screenshots.

visiontools

497