NVIDIA GeForce RTX 5060 Ti 16GB × Llama 4 Scout (17B active, 16 experts)
Can the RTX 5060 Ti 16GB run Llama 4 Scout (17B active, 16 experts)?
No
No. Llama 4 Scout (17B active, 16 experts) needs at least ~57.1 GB, but the RTX 5060 Ti 16GB has ~15.2 GB usable. You would need CPU offloading (much slower) or more memory.
By quantization (8K context)
| Quant | Memory needed | Fits? | Est. tok/s |
|---|---|---|---|
| Q3_K_M | 57.1 GB | ❌ | — |
| Q4_K_M | 70.5 GB | ❌ | — |
| Q5_K_M | 82.4 GB | ❌ | — |
| Q6_K | 95.0 GB | ❌ | — |
| Q8_0 | 122 GB | ❌ | — |
| F16 | 227 GB | ❌ | — |
Fastest hardware for Llama 4 Scout (17B active, 16 experts)
- Apple M5 Max (40-core GPU, 128GB) — ~26.9 tok/s at Q4_K_M
- Apple M2 Ultra (76-core GPU, 192GB) — ~21.1 tok/s at Q4_K_M
- Apple M3 Ultra (80-core GPU, 512GB) — ~20.7 tok/s at Q4_K_M
- Apple M4 Max (40-core GPU, 128GB) — ~18.6 tok/s at Q4_K_M
- NVIDIA DGX Spark — ~12.8 tok/s at Q4_K_M
Rent a GPU instead
Llama 4 Scout (17B active, 16 experts) doesn't fit here? Rent a cloud GPU with enough VRAM by the hour and run it there.
Vast.ai — cheap marketplace GPUs · RunPod — on-demand GPU pods
Affiliate links: we may earn a commission at no extra cost to you.
Get new models & benchmarks in your inbox
No spam. Unsubscribe anytime by replying to any email.