More
Submit build

Can RTX 5090 run Boole 32B-A2.5B Preview?

Last updated:

Yes. Measured 565.8 tok/s generation (llama.cpp fork (PrecisionNumerics), Q2_0 GGUF, 1.8 bits/weight average for routed experts (9.0 GB); source).

Every measured result for Boole 32B-A2.5B Preview on RTX 5090

BuildQuant / setupEnginetok/s
RTX 5090: Boole-32B-A2.5B Preview (1.8-bit Flint, 9 GB) at 565.8 tok/s vs Flint INT4 279.4 on llama.cpp (Precision Numerics)Q2_0 GGUF, 1.8 bits/weight average for routed experts (9.0 GB)llama.cpp fork (PrecisionNumerics)565.8source

Memory: RTX 5090 has 32 GB. Boole 32B-A2.5B Preview weights are about 19.6 GB at Q4_K_M (32B 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 Boole 32B-A2.5B Preview: best home rig for Boole 32B-A2.5B Preview.

Other models measured on RTX 5090: DeepSeek V4.1 Flash · Flint 40B-A2.5B · GLM-5.3 Flash · Gemma 4 12B · Gemma 4 26B-A4B · Gemma 4 31B · Nemotron 3.5 Bolt 74B-A9B · Ornith 1.5 122B · Ornith 1.5 35B-A3B · Qwen3.5 9B · Qwen3.6 27B · Qwen3.6 35B-A3B · Qwen3.8 27B · Qwen3.8 Flash-Next · gpt-oss 20B

Not enough VRAM? Rent before you buy. Run Boole 32B-A2.5B 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.