Can I Run Granite 3.0 on RTX 5080 Desktop (16 GB VRAM, 32 GB RAM)?

Superseded model. Granite 3.0 has been superseded by IBM Granite 4.0. This page is kept for reference; the newer family is a better starting point. View IBM Granite 4.0 →

Written by Jakub Rusinowski · Last updated October 21, 2024

Yes — comfortably

Yes, comfortably — Granite 3.0 8B Instruct at Q8_0 needs about 10.6 GB of the 16 GB usable on RTX 5080 Desktop (16 GB VRAM, 32 GB RAM), leaving ~5.4 GB spare and running at ~66.7 tok/s (estimated), with room for about 32,768 tokens of context.

Confidence: high · Recommended quantization: Q8_0 · Estimated speed: ~66.7 tok/s

RTX 5080 Desktop (16 GB VRAM, 32 GB RAM) — what it gives a model

Usable memory for models	16 GB
Memory bandwidth	960 GB/s
Form factor	Desktop
Operating system	Windows or Linux
Memory upgradeable	Yes

Granite 3.0 on RTX 5080 Desktop (16 GB VRAM, 32 GB RAM): memory by quantization

Quant	Memory needed	Fits 16 GB?	Max context	Est. speed	Download
F16	18.1 GB	✗ No	—	—	16 GB
Q8_0	10.6 GB	✓ Yes	32K	~66.7 tok/s	8.5 GB
Q6_K	8.7 GB	✓ Yes	32K	~81.4 tok/s	6.6 GB
Q5_K_M	7.8 GB	✓ Yes	32K	~90.5 tok/s	5.7 GB
Q4_K_M	7 GB	✓ Yes	32K	~101.1 tok/s	4.8 GB
Q3_K_M	5.6 GB	✓ Yes	64K	~126.4 tok/s	3.4 GB
Q2_K	4.8 GB	✓ Yes	64K	~146.4 tok/s	2.6 GB

RTX 5080 desktop limitations

16 GB VRAM is the binding constraint, not compute — a slower 24 GB card runs strictly more models.

Recommended setup

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

How these numbers are calculated

Memory need = quantized weights + KV cache at 8,192 tokens (f16) + 0.8 GB runtime overhead.
16 GB of VRAM on the NVIDIA GeForce RTX 5080 at 960 GB/s.
32 GB of system RAM available for CPU offload when a model exceeds VRAM.
Throughput is a memory-bandwidth roofline estimate, not a measurement. It is labelled "estimated" everywhere it appears.
KV cache is computed from this model's published attention configuration.

FAQ