# Llama 4 Scout 17B-16E Instruct

> OnPrem World · https://onpremworld.com/en/models/llama-4-scout · Last updated: 2026-10-16 · CC BY 4.0

A MoE with 109B total and 17B active parameters that also reads images. At 4-bit it needs a 72 GB card or a 96 GB unified-memory machine.

|  |  |
|---|---|
| Developer | Meta |
| Parameters | 109B (17B active, MoE) |
| Native context | 10,485,760 tokens |
| Licence | Llama 4 Community License |
| Commercial use | Yes |
| KV cache | 12 global + 36 chunked layers (8192 tokens) |
| Released | 2025-04 |

```
ollama run llama4:16x17b
```

## Memory needed

Weights + KV cache + runtime overhead, in GiB. Lower quantization = less memory, slightly lower quality.

| Quantization | 4K | 8K | 32K |
|---|---|---|---|
| Q4_K_M | 65.9 GiB | 66.6 GiB | 67.7 GiB |
| Q5_K_M | 77.1 GiB | 77.8 GiB | 78.9 GiB |
| Q6_K | 89.1 GiB | 89.8 GiB | 90.9 GiB |
| Q8_0 | 114.5 GiB | 115.3 GiB | 116.4 GiB |
| FP16 | 214.4 GiB | 215.2 GiB | 216.3 GiB |

## Which hardware runs it (8K)

| Hardware | Memory | Best quant | tok/s (est.) |
|---|---|---|---|
| DGX Station (GB300) | 252 GB | FP16 | 113 |
| RTX PRO 5000 72GB Blackwell | 72 GB | Q4_K_M | 77 |
| RTX PRO 6000 Blackwell Workstation Edition | 96 GB | Q6_K | 76 |
| RTX PRO 6000 Blackwell Max-Q Workstation Edition | 96 GB | Q6_K | 76 |
| M5 Max (18-core CPU / 40-core GPU) | 128 GB | Q6_K | 27 |
| M4 Max (16-core CPU / 40-core GPU) | 128 GB | Q6_K | 24 |
| M5 Ultra | 512 GB | FP16 | 22 |
| M3 Ultra | 512 GB | FP16 | 15 |
| RTX Spark (N1X) laptops & compact desktops | 128 GB | Q6_K | 13 |
| DGX Spark | 128 GB | Q6_K | 11 |
| Ryzen AI Max+ 395 (Strix Halo) systems | 128 GB | Q6_K | 11 |
| Ryzen AI Max+ PRO 495 (Gorgon Halo) systems | 192 GB | Q8_0 | 8.9 |
| GeForce RTX 3060 (12 GB) | 12 GB | Doesn't fit | – |
| GeForce RTX 3090 | 24 GB | Doesn't fit | – |
| GeForce RTX 4060 Ti 16GB | 16 GB | Doesn't fit | – |
| GeForce RTX 4080 SUPER | 16 GB | Doesn't fit | – |
| GeForce RTX 4090 | 24 GB | Doesn't fit | – |
| GeForce RTX 5060 Ti 16GB | 16 GB | Doesn't fit | – |
| GeForce RTX 5070 | 12 GB | Doesn't fit | – |
| GeForce RTX 5070 Ti | 16 GB | Doesn't fit | – |
| GeForce RTX 5080 | 16 GB | Doesn't fit | – |
| GeForce RTX 5090 | 32 GB | Doesn't fit | – |
| Radeon RX 7900 XT | 20 GB | Doesn't fit | – |
| Radeon RX 7900 XTX | 24 GB | Doesn't fit | – |
| Radeon RX 9060 XT 16GB | 16 GB | Doesn't fit | – |
| Radeon RX 9070 XT | 16 GB | Doesn't fit | – |
| Arc B580 | 12 GB | Doesn't fit | – |
| RTX A6000 | 48 GB | Doesn't fit | – |
| RTX 6000 Ada Generation | 48 GB | Doesn't fit | – |
| Radeon AI PRO R9700 | 32 GB | Doesn't fit | – |
| Arc Pro B60 | 24 GB | Doesn't fit | – |
| Arc Pro B70 | 32 GB | Doesn't fit | – |
| M4 Pro | 64 GB | Doesn't fit | – |
| M4 Max (14-core CPU / 32-core GPU) | 36 GB | Doesn't fit | – |
| M5 | 32 GB | Doesn't fit | – |
| M5 Pro | 64 GB | Doesn't fit | – |
| M5 Max (18-core CPU / 32-core GPU) | 36 GB | Doesn't fit | – |
| M6 (16GB configuration, 153 GB/s) | 16 GB | Doesn't fit | – |
| M6 (24GB/32GB configurations, 170 GB/s) | 32 GB | Doesn't fit | – |
| RTX PRO 5000 48GB Blackwell | 48 GB | Doesn't fit | – |
| RTX PRO 4500 Blackwell | 32 GB | Doesn't fit | – |
| RTX PRO 4000 Blackwell | 24 GB | Doesn't fit | – |

## Frequently asked questions

### How much VRAM does Llama 4 Scout 17B-16E Instruct need?

With an 8K context, about 66.6 GiB at Q4_K_M and 115.3 GiB at Q8_0 (weights + KV cache + runtime overhead). Longer contexts need more memory for the KV cache.

### Can Llama 4 Scout 17B-16E Instruct run on an GeForce RTX 4090?

Llama 4 Scout 17B-16E Instruct does not fit on the GeForce RTX 4090 (24 GB), even at Q4_K_M with an 8K context.

### Can I run Llama 4 Scout 17B-16E Instruct on a Mac?

Yes. Llama 4 Scout 17B-16E Instruct fits on the M3 Ultra (96 GB) at Q4_K_M with an 8K context, using about 66.6 GiB, at an estimated 47 tokens/s.

### Can Llama 4 Scout 17B-16E Instruct be used commercially?

Llama 4 Scout 17B-16E Instruct is released under Llama 4 Community License. The licence allows commercial use (read its conditions).

## Sources

- https://github.com/meta-llama/llama-models/blob/main/models/llama4/MODEL_CARD.md
- https://github.com/meta-llama/llama-models/blob/main/models/llama4/LICENSE
- https://huggingface.co/RedHatAI/Llama-4-Scout-17B-16E-Instruct/resolve/main/config.json
- https://huggingface.co/meta-llama/Llama-4-Scout-17B-16E-Instruct
- https://huggingface.co/api/models/meta-llama/Llama-4-Scout-17B-16E-Instruct?expand[]=safetensors
- https://ollama.com/library/llama4/tags