Running GLM-5.3-Flash on 2× DGX Spark with NVIDIA Flare ✨
- 1M context window, 2.32M-token shared KV pool
- Prose decode, single stream: 117.2 tok/s
- Prose decode, 2 concurrent: 167.4 tok/s aggregate
- Prose decode, 4 concurrent: 215.8 tok/s aggregate
- 32K prefill: 2,327.9 tok/s
- Available memory after loading: ~13 GiB on head /worker each
Checkpoint: GLM-5.3-Flash-NVFP4-MXFP8-CSF-QAD
Show more
