Can I Run GLM-5 / GLM-5.1 on RTX 5090 Desktop (32 GB VRAM, 64 GB RAM)?

Written by Jakub Rusinowski · Last updated May 1, 2026

Yes, but it is tight

Yes, but it is tight — GLM-5 32B 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 ~44.5 tok/s (estimated), with room for about 16,384 tokens of context.

Confidence: low · Recommended quantization: Q6_K · Estimated speed: ~44.5 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

GLM-5 / GLM-5.1 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~44.5 tok/s26.2 GB
Q5_K_M25.3 GB✓ Yes32K~50.5 tok/s22.7 GB
Q4_K_M22 GB✓ Yes32K~57.8 tok/s19.3 GB
Q3_K_M16.3 GB✓ Yes64K~76.4 tok/s13.6 GB
Q2_K13.2 GB✓ Yes64K~92.9 tok/s10.5 GB

Which GLM-5 / GLM-5.1 sizes fit

VariantNeeds at Q4_K_MFits?Est. speed
GLM-5 744B455.2 GB✗ Too large
GLM-5.1 72B46.7 GB✗ Too large
GLM-5 32B22 GB✓ Fits~57.8 tok/s
GLM-5 9B7.4 GB✓ Fits~148.4 tok/s

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 GLM-5 / GLM-5.1 on RTX 5090 Desktop (32 GB VRAM, 64 GB RAM)?

Yes, but it is tight — GLM-5 32B 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 ~44.5 tok/s (estimated), with room for about 16,384 tokens of context.

Which quantization of GLM-5 / GLM-5.1 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 44.5 tokens/sec with up to 16K of context.

What limits GLM-5 / GLM-5.1 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)

GLM-5 / GLM-5.1 on GPUs

What This Model Is Good At

Model & Tools

← Can I Run It? | GLM-5 / GLM-5.1 model page | Check your hardware