Can 4x DGX Spark (GB10) run Step 5 Preview?
Yes. Measured 25 tok/s generation (vLLM, TP=4 over RoCE, MTP (2 draft tokens), EXL3 (experts 4.01 bpw, 341.4 GB total); source).
Every measured result for Step 5 Preview on 4x DGX Spark (GB10)
| Build | Quant / setup | Engine | tok/s | |
|---|---|---|---|---|
| 4x DGX Spark (GB10) running Step 5 Preview with tensor parallel over RoCE | EXL3 (experts 4.01 bpw, 341.4 GB total) | vLLM, TP=4 over RoCE, MTP (2 draft tokens) | 25 | source |
Memory: 4x DGX Spark (GB10) has 512 GB. Step 5 Preview weights are about 367.1 GB at Q4_K_M (600B 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 Step 5 Preview: best home rig for Step 5 Preview.
Other models measured on 4x DGX Spark (GB10): GLM-5.2 · GLM-5.3 Flash
Not enough VRAM? Rent before you buy. Run Step 5 Preview 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.