Can I Run Llama 3.3 on RTX 5090 Desktop (32 GB VRAM, 64 GB RAM)?
Superseded model. Llama 3.3 has been superseded by Llama 4. This page is kept for reference; the newer family is a better starting point.
View Llama 4 →
Written by Jakub Rusinowski · Last updated December 8, 2024
Yes
Yes — Llama 3.3 70B Instruct at Q2_K needs about 26.5 GB of the 32 GB usable on RTX 5090 Desktop (32 GB VRAM, 64 GB RAM) (~5.5 GB spare), at ~49.1 tok/s (estimated), with room for about 16,384 tokens of context.
Confidence: high · Recommended quantization: Q2_K · Estimated speed: ~49.1 tok/s
RTX 5090 Desktop (32 GB VRAM, 64 GB RAM) — what it gives a model
| Usable memory for models | 32 GB |
| Memory bandwidth | 1792 GB/s |
| Form factor | Desktop |
| Operating system | Windows or Linux |
| Memory upgradeable | Yes |
Llama 3.3 on RTX 5090 Desktop (32 GB VRAM, 64 GB RAM): memory by quantization
| Quant | Memory needed | Fits 32 GB? | Max context | Est. speed | Download |
|---|
| F16 | 143.5 GB | ✗ No | — | — | 140 GB |
| Q8_0 | 77.9 GB | ✗ No | — | — | 74.4 GB |
| Q6_K | 60.9 GB | ✗ No | — | — | 57.4 GB |
| Q5_K_M | 53.1 GB | ✗ No | — | — | 49.6 GB |
| Q4_K_M | 45.7 GB | ✗ No | — | — | 42.3 GB |
| Q3_K_M | 33.3 GB | ✗ No | — | — | 29.8 GB |
| Q2_K | 26.5 GB | ✓ Yes | 16K | ~49.1 tok/s | 23 GB |
What to watch out for
- Q2_K is the only quantization that fits, and it is a heavily degraded one — expect noticeably worse output than the same model at Q4_K_M. A smaller model at Q4 is usually the better trade.
- 1 larger variant of Llama 3.3 does not fit and would need CPU offload or different hardware.
RTX 5090 desktop limitations
- 575 W board power — budget for a 1000 W+ PSU and the heat it puts into the room.
- Models larger than 32 GB must offload to system RAM, which costs roughly an order of magnitude in speed.
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.
- 32 GB of VRAM on the NVIDIA GeForce RTX 5090 at 1792 GB/s.
- 64 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
Can I run Llama 3.3 on RTX 5090 Desktop (32 GB VRAM, 64 GB RAM)?
Yes — Llama 3.3 70B Instruct at Q2_K needs about 26.5 GB of the 32 GB usable on RTX 5090 Desktop (32 GB VRAM, 64 GB RAM) (~5.5 GB spare), at ~49.1 tok/s (estimated), with room for about 16,384 tokens of context.
Which quantization of Llama 3.3 should I use on RTX 5090 Desktop (32 GB VRAM, 64 GB RAM)?
Q2_K — it needs about 26.5 GB of the 32 GB available, downloads as roughly 23 GB, and runs at an estimated 49.1 tokens/sec with up to 16K of context.
What limits Llama 3.3 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)
Llama 3.3 on GPUs
What This Model Is Good At
Model & Tools
← Can I Run It? | Llama 3.3 model page | Check your hardware