Can the RTX 3090 run Llama 3.3 70B?
No. Llama 3.3 70B needs about 41.8 GB at Q4_K_M (weights plus 1.8 GB runtime overhead), and the RTX 3090 has 24 GB, so it won't fit without offloading layers to system RAM, which is far slower.
Every quantization
Llama 3.3 70B (70B) on 24 GB
| Quant | Weights | Needs | Fit | Est. speed |
|---|---|---|---|---|
| Q4_K_M | 40 GB | 41.8 GB | Too big | - |
| Q5_K_M | 48 GB | 49.8 GB | Too big | - |
| Q8_0 | 75 GB | 76.8 GB | Too big | - |
| FP16 | 140 GB | 141.8 GB | Too big | - |
Estimates. Needs = weights + 1.8 GB for KV cache and runtime at modest context. Speed is single-stream decode scaled from the RTX 3090's 936 GB/s bandwidth (XiongjieDai/GPU-Benchmarks-on-LLM-Inference). Long contexts need more memory and run slower.
What to do instead
Two ways forward
Cheapest cards that run it
- NVIDIA RTX A6000 - 48 GB, ~$3,299
- Mac Studio M4 Ultra - 192 GB, ~$4,699
- NVIDIA RTX 6000 Ada Generation - 48 GB, ~$5,800
- NVIDIA L40S - 48 GB, ~$8,500
Models that fit the RTX 3090
- GLM-4.7-Flash - 31.2B, 18 GB at Q4
- Qwen3-30B-A3B-Instruct-2507 - 30.5B, 18 GB at Q4
- Qwen3.6 27B - 28B, 16 GB at Q4
- Qwen3.8 27B - 27.8B, 16 GB at Q4
Compare
Same model, other hardware - and other models on this card
Llama 3.3 70B on other hardware
- RTX 6000D~23 tok/s
- MacBook Pro 16" M4 Max~7.8 tok/s
- DGX Spark (GB10)~3.9 tok/s
- RTX Spark N1X (128 GB)~3.9 tok/s
Also runs on the RTX 3090
- GLM-4.7-Flash~211 tok/s
- Qwen3-30B-A3B-Instruct-2507~206 tok/s
- Qwen3.6 27B~34 tok/s
- Qwen3.8 27B~34 tok/s
- Gemma 4 26B A4B~161 tok/s
- gpt-oss-20b~182 tok/s
- Qwen2.5-Coder-14B-Instruct~61 tok/s
- Qwen3 14B~68 tok/s
Frequently asked
Quick answers
Can the NVIDIA RTX 3090 run Llama 3.3 70B?
No. Llama 3.3 70B needs about 41.8 GB at Q4_K_M (weights plus 1.8 GB runtime overhead), and the RTX 3090 has 24 GB, so it won't fit without offloading layers to system RAM, which is far slower.
How much VRAM does Llama 3.3 70B need?
About 40 GB of weights at Q4_K_M, 75 GB at Q8_0 and 140 GB at FP16. Add roughly 1.8 GB for the KV cache and runtime at modest context lengths.
How fast is Llama 3.3 70B on the RTX 3090?
It doesn't fit in the RTX 3090's memory, so speed depends on how many layers you offload to system RAM - typically single-digit tokens per second or lower.