Can I Run IBM Granite 4.0 on RTX 5090 Desktop (32 GB VRAM, 64 GB RAM)?

Written by Jakub Rusinowski · Last updated August 15, 2026

Yes, but it is tight

Yes, but it is tight — Granite 4.0 Small-H 32B-A9B at Q6_K needs about 28.9 GB of the 32 GB usable on RTX 5090 Desktop (32 GB VRAM, 64 GB RAM), leaving only ~3.1 GB before the runtime starts swapping. Expect ~118.7 tok/s (estimated), with room for about 16,384 tokens of context.

Confidence: low · Recommended quantization: Q6_K · Estimated speed: ~118.7 tok/s

RTX 5090 Desktop (32 GB VRAM, 64 GB RAM) — what it gives a model

Usable memory for models32 GB
Memory bandwidth1792 GB/s
Form factorDesktop
Operating systemWindows or Linux
Memory upgradeableYes

IBM Granite 4.0 on RTX 5090 Desktop (32 GB VRAM, 64 GB RAM): memory by quantization

QuantMemory neededFits 32 GB?Max contextEst. speedDownload
F1666.6 GB✗ No64 GB
Q8_036.6 GB✗ No34 GB
Q6_K28.9 GB✓ Yes16K~118.7 tok/s26.2 GB
Q5_K_M25.3 GB✓ Yes32K~130.2 tok/s22.7 GB
Q4_K_M22 GB✓ Yes32K~143.4 tok/s19.3 GB
Q3_K_M16.3 GB✓ Yes64K~172.8 tok/s13.6 GB
Q2_K13.2 GB✓ Yes64K~194.8 tok/s10.5 GB

What to watch out for

RTX 5090 desktop limitations

Recommended setup

Ollama or llama.cpp (CUDA/ROCm) — vLLM if you need concurrent serving

How these numbers are calculated

FAQ

Can I run IBM Granite 4.0 on RTX 5090 Desktop (32 GB VRAM, 64 GB RAM)?

Yes, but it is tight — Granite 4.0 Small-H 32B-A9B at Q6_K needs about 28.9 GB of the 32 GB usable on RTX 5090 Desktop (32 GB VRAM, 64 GB RAM), leaving only ~3.1 GB before the runtime starts swapping. Expect ~118.7 tok/s (estimated), with room for about 16,384 tokens of context.

Which quantization of IBM Granite 4.0 should I use on RTX 5090 Desktop (32 GB VRAM, 64 GB RAM)?

Q6_K — it needs about 28.9 GB of the 32 GB available, downloads as roughly 26.2 GB, and runs at an estimated 118.7 tokens/sec with up to 16K of context.

What limits IBM Granite 4.0 on RTX 5090 Desktop (32 GB VRAM, 64 GB RAM)?

Nothing binding — the model fits with headroom and generates at a usable speed on this hardware.

Which runtime should I use?

Ollama or llama.cpp (CUDA/ROCm) — vLLM if you need concurrent serving

Other Computers

Other Models on RTX 5090 Desktop (32 GB VRAM, 64 GB RAM)

IBM Granite 4.0 on GPUs

What This Model Is Good At

Model & Tools

← Can I Run It? | IBM Granite 4.0 model page | Check your hardware