Can 4x DGX Spark (GB10) run GLM-5.2?
Yes. Measured 32.5 tok/s generation (vLLM TP4 + MTP, single-stream mean, QuantTrio Int4-Int8Mix; source).
Every measured result for GLM-5.2 on 4x DGX Spark (GB10)
| Build | Quant / setup | Engine | tok/s | |
|---|---|---|---|---|
| 4x DGX Spark cluster running GLM-5.2 (unpruned) | QuantTrio Int4-Int8Mix | vLLM TP4 + MTP, single-stream mean | 32.5 | source |
Memory: 4x DGX Spark (GB10) has 512 GB. GLM-5.2 weights are about 460.9 GB at Q4_K_M (753.3B params × 4.89 bits ÷ 8, before context/KV cache). Arithmetic, not a measurement; long contexts need more. Check other quants in the VRAM calculator.
Speeds are decode (generation) tokens/sec as reported by each source; quant, engine and context differ, so small gaps are noise.
All measured speeds for GLM-5.2: best home rig for GLM-5.2.
Other models measured on 4x DGX Spark (GB10): GLM-5.3 Flash
Not enough VRAM? Rent before you buy. Run GLM-5.2 on a bigger GPU on a rented 24–96 GB cloud GPU by the hour and see the real speed before spending €1,000+. Try it on Runpod
Referral link: if you sign up with Google and add $10, Runpod gives you and RigBase bonus credit (terms). It never affects our data.
Referral link: if you sign up with Google and add $10, Runpod gives you and RigBase bonus credit (terms). It never affects our data.