MXFP4 · 4K context
Ling-3.0-flash-VL MoE model with 124.848460496B total parameters and 5.1B active per token · estimated MXFP4 memory about 71GB
An image/video-input MoE model with about 124.85B total and 5.1B active parameters. Native context is 128K. Only official DGX Spark INT4/MXFP4 measurements anchor the speed experience; rates are not transferred to other hardware.
- Estimated MXFP4 memory
- About 71GB
- total parameters
- 124.848460496B
- active parameter
- 5.1B
- native context
- 128K
Representative equipment to run this model
Decode
33.13 tok/s · 8K measurement anchor
First token
1.27 s · Estimated
Running Guide
Ling-3.0-flash-VL Local Serving Run Recipe
Selecting a device changes the quantization, safety context, GPU offload, Flash Attention, KV cache, and batch start values.
If you want to choose equipment again
You can first narrow down the model configurations based on budget, noise level, operating system and whether it's acceptable used.