Loading…
Loading…
Models / Qwen3.8-Flash-Next-E384-FP4
GPU memory needed (smallest version of each): Qwen3.8-Flash-Next-E384-FP4 ~155B about 100.6 GB. The cheapest runs on Nvidia GB10 from $0.38/h right now.
1 model (~155B) · ↓ 72.5K downloads a month · from $0.38/h on Nvidia GB10 right now. Each model's versions do the same job; quantized ones (AWQ, FP8, 4-bit) need less GPU memory and run on cheaper machines.
Model details come from Hugging Face and are refreshed daily; prices follow the live offers. GPU memory is GridPup's estimate: the weights, room for an 8,192-token conversation (chat models) and the runtime's own memory. Large models are split across the GPUs of one machine ("4x RTX 4090").