Builds / 4x Nvidia GB10 (unified, DGX Spark)
4x DGX Spark ring running GLM-5.3 Flash NVFP4
Source: github.com ↗📏 How measured: reported by the original source; RigBase re-checked the numbers at that source
- GPU(s)
- 4x Nvidia GB10 (unified, DGX Spark)
- VRAM / unified memory (GB)
- 512
- CPU
- Nvidia Grace 20-core (per node)
Amazon · eBay (used) · Newegg - Motherboard
- not stated
- RAM
- 128 GB unified per node
- PSU
- not stated
- Other
- Switchless ConnectX-7 ring; vLLM TP4
- Reported total cost
- not stated
- Power
- not stated
Measured speed (generation tokens/sec)
| Model | Quant | Engine | tok/s | Details |
|---|---|---|---|---|
| GLM-5.3 Flash | NVFP4 | vLLM TP4 (RiNGSiDE), single-stream prose | 61.7 | 📏 Single-stream decode reported by the source |
| GLM-5.3 Flash | NVFP4 | vLLM TP4 (RiNGSiDE), single-stream code | 105.3 | 📏 Single-stream decode reported by the source |
RedHatAI checkpoint; structured output reaches 145.4 tok/s. vram_gb is aggregate unified memory. Found via localmaxxing (discovery only); numbers re-checked at the original source on 2026-10-24.
Source: https://github.com/othexmr/GLM-5.3-Flash-NVFP4-2x-4x-DGX-Sparks-RiNGSiDE
Blank fields = not stated in the source. We never estimate build data; GPU street prices above are separately sourced and dated.
Rent before you buy: try this model on a cloud GPU for a few dollars first: Runpod (referral link; sign up with Google to get the new-user bonus)
Quick answers: Can 4x DGX Spark (GB10) run GLM-5.3 Flash?