Llama 4 Scout 17B-16E Instruct
Llama 4 Scout 17B-16E Instruct by Meta (109B parameters, MoE with 17B active per token). At Q4_K_M with an 8K context it needs about 66.6 GiB of memory. 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.
Last updated: 2026-10-13
Model facts
Run it
ollama run llama4:16x17b
Memory needed
Weights + KV cache + runtime overhead, in GiB. Lower quantization = less memory, slightly lower quality.
| Quantization | 4K context | 8K context | 32K context |
|---|---|---|---|
| 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
Best quantization that fits each device with a 8K context. Estimates, not benchmarks. See the methodology.
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 52 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