text model · llama · Windows
Can I run Llama 3.3 70B on Nvidia GeForce RTX 3090 (24GB)?
No. Llama 3.3 70B needs ~45.3 GB even at Q4_K_M, but Nvidia GeForce RTX 3090 (24GB) only has ~23 GB usable.
Needs ~45.3 GB even at Q4_K_M, but only ~23 GB is usable.
- Q4_K_M needed
- ~45.3 GB
- Usable on device
- ~23 GB
- Device memory
- 24 GB
- Parameters
- 70B
- Q4_K_M size
- 42.52 GB
- Q8_0 size
- 74.98 GB
- Context
- 128k
- Ollama tag
- llama3.3:70b
- Memory
- 24 GB vram
- Usable for weights
- ~23 GB
- Best runtime
- vLLM (Linux) / Ollama (CUDA)
What you can run instead
Run Llama 3.3 70B on other hardware
FAQ
Can Nvidia GeForce RTX 3090 (24GB) run Llama 3.3 70B?
No. Llama 3.3 70B needs ~45.3 GB even at Q4_K_M, but Nvidia GeForce RTX 3090 (24GB) only has ~23 GB usable.
How much memory does Llama 3.3 70B need?
Nvidia GeForce RTX 3090 (24GB) does not have enough memory. At Q4_K_M the weights are ~42.52 GB; with KV cache and runtime overhead, budget ~45.3 GB at a 4k context.
What is the best tool to run Llama 3.3 70B on Windows?
LM Studio for a simple setup; Ollama (CUDA) for the most speed. AMD GPUs run via Vulkan/ROCm at roughly half CUDA throughput. NVIDIA is the smooth path on Windows.
Sources
Memory figures are estimates. See methodology.