# Can I run Llama 4 Scout on Nvidia GeForce RTX 5090 (32GB)?

> **No, not enough memory.** Needs ~64.2 GB even at Q4_K_M, but only ~31 GB is usable.

Last validated: 2026-06-15.

## Memory math
- Llama 4 Scout: 109B (MoE, 17B active); Q4_K_M weighs 60.87 GB on disk.
- At Q4_K_M with a 4k context it needs ~64.2 GB (weights + KV cache + ~0.8 GB runtime overhead, ±15% with context length).
- Nvidia GeForce RTX 5090 (32GB): 32 GB vram, ~31 GB usable for model weights.
- Headroom: ~-33.2 GB.

## How to run
Recommended quant: n/a. Best tool on Windows: LM Studio.

```sh
ollama run llama4:scout
```

## Run Llama 4 Scout on other devices
- [Apple M4 Max (128GB)](https://localmodel.run/can-i-run/llama-4-scout/apple-m4-max-128gb)
- [Apple M5 Max (128GB)](https://localmodel.run/can-i-run/llama-4-scout/apple-m5-max-128gb)
- [Apple M3 Ultra (256GB)](https://localmodel.run/can-i-run/llama-4-scout/apple-m3-ultra-256gb)

## Other models that run on Nvidia GeForce RTX 5090 (32GB)
- [Mixtral 8x7B (46.7B)](https://localmodel.run/can-i-run/mixtral-8x7b/nvidia-rtx-5090-32gb)
- [Command R 35B (35B)](https://localmodel.run/can-i-run/command-r-35b/nvidia-rtx-5090-32gb)
- [Yi 1.5 34B (34B)](https://localmodel.run/can-i-run/yi-1.5-34b/nvidia-rtx-5090-32gb)
- [Qwen2.5 32B (32B)](https://localmodel.run/can-i-run/qwen2.5-32b/nvidia-rtx-5090-32gb)
- [Qwen3 32B (32B)](https://localmodel.run/can-i-run/qwen3-32b/nvidia-rtx-5090-32gb)
- [DeepSeek-R1-Distill-Qwen 32B (32B)](https://localmodel.run/can-i-run/deepseek-r1-distill-qwen-32b/nvidia-rtx-5090-32gb)

Estimate, not a guarantee. Sources: https://ollama.com/library/llama4, https://ollama.com/library/llama4/tags, https://huggingface.co/unsloth/Llama-4-Scout-17B-16E-Instruct-GGUF, https://huggingface.co/meta-llama/Llama-4-Scout-17B-16E-Instruct.
More: https://localmodel.run/can-i-run/llama-4-scout/nvidia-rtx-5090-32gb