以超低成本在任何硬體上部署 MiniMax-H3-Image!🤖 https://t.co/eWqwgVRZbU
EntroPack 現在可實現快速、低成本的推論。選擇你的 checkpoint:🔹 80GB VRAM:bf16_table_pruned.safetensors(完全無損的剪枝模型)🔹 24GB VRAM:dit_8bit_int8.safetensors(近乎無損的 INT8 + ConvRot 量化)🔹 8GB VRAM:dit_extreme_3bpp.safetensors(極限 3-bit 量化模型)
模型儲存庫也提供 ComfyUI 工作流程。立即試用!
AI 伴隨問答
針對這篇報導有疑問?可直接點選快捷問題或向 AI 追問背景脈絡與技術細節:
Deploy MiniMax-H3-Image on ANY hardware with ultra-low cost! 🤖 https://t.co/eWqwgVRZbU
Fast, low-cost inference is now possible with EntroPack. Choose your checkpoint:
🔹 80GB VRAM: bf16_table_pruned.safetensors (Fully lossless pruned model)
🔹 24GB VRAM: dit_8bit_int8.safetensors (Near-lossless INT8 + ConvRot quantization)
🔹 8GB VRAM: dit_extreme_3bpp.safetensors (Extreme 3-bit quantized model)
ComfyUI workflows also available in the model repository. Try it now!