Qwen 3.8 Flash Next BF16 on 4x Nvidia DGX Sparks is also great at making dioramas.
Local AI is getting good... Im sure the NVFP4 version (which you can run on 1-2 sparks) is almost just as good as this one as well One-shot output with the prompt below 👇
DeepSeek-V4-Flash-Vision, Qwen 3.8 Max, Claude credits, and agent compute - all FREE right now.
HuggingFace: DeepSeek-V4-Flash-Vision-Exp, 305B, first multimodal DeepSeek, MIT open weights: Qwen Chat: Qwen 3.8 Max free, 1M context, image input, zero
Qwen 3.8 Flash Next 180B (80gb) on android mobile phone 12gb RAM (400$ phone)...
Qwen 3.8 Flash Next 180B (80gb) on android mobile phone 12gb RAM (400$ phone)...
You have reached the end of the archive
All of qwen38