text model · llama · Windows
Can I run Llama 3.1 8B on Nvidia GeForce RTX 4080 (16GB)?
Yes. Llama 3.1 8B runs on Nvidia GeForce RTX 4080 (16GB) at Q4_K_M (~6.4 GB of ~15 GB usable).
Runs at Q4_K_M using ~6.4 GB of ~15 GB usable. You have room for Q8_0 for higher quality.
- Q4_K_M needed
- ~6.4 GB
- Usable on device
- ~15 GB
- Device memory
- 16 GB
- Best quant
- Q4_K_M
Run it
Pick your tool. All three load the same Q4_K_M weights.
ollama run llama3.1:8b llama-cli -hf bartowski/Meta-Llama-3.1-8B-Instruct-GGUF:Q4_K_M lms get bartowski/Meta-Llama-3.1-8B-Instruct-GGUF AMD GPUs run via Vulkan/ROCm at roughly half CUDA throughput. NVIDIA is the smooth path on Windows.
- Parameters
- 8B
- Q4_K_M size
- 4.92 GB
- Q8_0 size
- 8.54 GB
- Context
- 128k
- Ollama tag
- llama3.1:8b
- Memory
- 16 GB vram
- Usable for weights
- ~15 GB
- Best runtime
- vLLM (Linux) / Ollama (CUDA)
You could also run
Run Llama 3.1 8B on other hardware
FAQ
Can Nvidia GeForce RTX 4080 (16GB) run Llama 3.1 8B?
Yes. Llama 3.1 8B runs on Nvidia GeForce RTX 4080 (16GB) at Q4_K_M (~6.4 GB of ~15 GB usable).
How much memory does Llama 3.1 8B need?
Nvidia GeForce RTX 4080 (16GB) has room to spare. At Q4_K_M the weights are ~4.92 GB; with KV cache and runtime overhead, budget ~6.4 GB at a 4k context.
What is the best tool to run Llama 3.1 8B 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.