Builds / 4x Nvidia GB10 (unified, DGX Spark)
4x DGX Spark cluster running GLM-5.2 (unpruned)
Source: github.com ↗📏 How measured: reported by the original source; RigBase re-checked the numbers at that source
Legacy models only. Every model measured on this rig now has a newer successor: GLM-5.2 → GLM-5.3. The hardware numbers are still a useful reference.
- GPU(s)
- 4x Nvidia GB10 (unified, DGX Spark)
- VRAM / unified memory (GB)
- 512
- CPU
- Nvidia Grace (per node)
Amazon · eBay (used) · Newegg - Motherboard
- not stated
- RAM
- 128 GB unified per node
- PSU
- not stated
- Other
- ConnectX-7 RoCE between nodes; vLLM multi-node TP4, MTP k=5
- Reported total cost
- not stated
- Power
- not stated
Measured speed (generation tokens/sec)
| Model | Quant | Engine | tok/s | Details |
|---|---|---|---|---|
| GLM-5.2 legacy | QuantTrio Int4-Int8Mix | vLLM TP4 + MTP, single-stream mean | 32.5 | ⚡ spec-decode (MTP)context: 200K max📏 Single-stream mean (source config of 2026-07-17) |
2026-07-17 config: 32.5 tok/s single-stream mean, 36.0 peak, 65-75 tok/s aggregate at 6 concurrent, 200K context. 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/tonyd2wild/GLM-5.2-QuantTrio-200K-4x-DGX-Spark
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-5.2?