INT8 quantized versions of the Qwen3-VL text encoders, for use in ComfyUI workflows (Boogu, Ideogram 4, and others that use Qwen3-VL as a text encoder).

All quantized with silveroxides/convert_to_quant, --int8 --scaling_mode tensor --simple, embedding/lm_head/norm layers excluded and kept in BF16.

⚠️ Do not use a text encoder requantized from an already-FP8-quantized source (FP8 → INT8). Double quantization causes visible color/saturation drift, especially noticeable on few-step distilled models like Boogu Turbo. These files were quantized directly from true BF16 source weights (Comfy-Org/Qwen3-VL), avoiding that issue entirely.

Load via the standard Load CLIP node in ComfyUI, paired with the matching diffusion model (Boogu, Ideogram 4, etc.). Native INT8 support is available in recent ComfyUI builds; older builds need an INT8-compatible custom node.

💬 Discord: discord.gg/CJv5wceJaN ☕ Ko-fi: ko-fi.com/winnougan