LL

Llama 4 Scout 17B 16E Instruct

LlamaGGUF by mradermacherUpdated 2025-07-11
Download on Hugging Face
Parameters108B
Context10240K
Layers48
Architecturellama4
Smallest quant22.2 GB
Quick answer

Llama 4 Scout 17B 16E Instruct needs about 39.1 GB of memory at Q2_K_S (a 37.0 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 13 quants, from 22.2 GB (IQ1_S) to 47.5 GB (IQ3_M). Longer context needs more: at 32K tokens the KV cache alone adds about 6.4 GB.

Llama 4 Scout 17B 16E Instruct – 108B Mixture of Experts model

Llama 4 Scout 17B 16E Instruct is a 108‑billion‑parameter Mixture of Experts model with a 10,485,760‑token context window. It is available in GGUF format with multiple quantization options. The model is released under an other license and supports multiple languages.

Good at

  • Large context generation
  • Mixture of Experts inference
  • High token capacity

Limits

  • Large VRAM requirement
  • No vision support in current GGUF
  • License not standard

Best for

  • Long‑form content creation
  • Research prototyping
  • Enterprise chatbots

Who it’s for. Developers and researchers needing a large‑context LLM with Mixture of Experts. Suitable for teams with GPU resources that can handle high VRAM demands.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S22.2 GB 24.3 GB
Too big Get file →
IQ1_M24.6 GB 26.7 GB
Too big Get file →
IQ2_XXS28.6 GB 30.7 GB
Too big Get file →
IQ2_XS31.8 GB 33.9 GB
Too big Get file →
IQ2_S32.3 GB 34.4 GB
Too big Get file →
IQ2_M35.5 GB 37.6 GB
Too big Get file →
Q2_K_S37.0 GB 39.1 GB
Too big Get file →
Q2_K39.6 GB 41.7 GB
Too big Get file →
IQ3_XXS41.7 GB 43.8 GB
Too big Get file →
IQ3_XS44.3 GB 46.4 GB
Too big Get file →
Q3_K_S46.7 GB 48.9 GB
Too big Get file →
IQ3_S46.8 GB 48.9 GB
Too big Get file →
IQ3_M47.5 GB 49.6 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (22.18 GB file, ~24.3 GB memory). For 12 GB VRAM, IQ1_M (24.57 GB file, ~26.7 GB memory). For 16 GB VRAM, IQ2_XXS (28.56 GB file, ~30.7 GB memory).

What GPU do you need for Llama 4 Scout 17B 16E Instruct?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: no quant fits at an 8K context.
  • 6 GB VRAM: no quant fits at an 8K context.
  • 8 GB VRAM: no quant fits at an 8K context.
  • 12 GB VRAM: no quant fits at an 8K context.
  • 16 GB VRAM: no quant fits at an 8K context.
  • 24 GB VRAM: no quant fits at an 8K context.
  • 32 GB VRAM: the best quant that fits is IQ2_XXS (28.6 GB file, about 30.7 GB in use).
  • 48 GB VRAM: the best quant that fits is IQ3_XS (44.3 GB file, about 46.4 GB in use).

Which Llama 4 Scout 17B 16E Instruct quant should you choose?

Q2_K_S (37.0 GB) is the middle option in this repository. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

If memory is tight, the smallest file is IQ1_S at 22.2 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama4
Parameters108B (approximate, mixture of experts)
Layers48
Trained context10,485,760 tokens
KV cache (fp16)192 KB per token

Source

Quantized bymradermacher
FamilyLlama
Licenseother
Downloads (HF)1,288
Last updated2025-07-11

Frequently asked questions about Llama 4 Scout 17B 16E Instruct

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

About 39.1 GB at Q2_K_S with an 8K context window. That is the 37.0 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run Llama 4 Scout 17B 16E Instruct on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 24.3 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Llama 4 Scout 17B 16E Instruct GGUF?

It depends on the quant: IQ1_S is 22.2 GB, IQ1_M is 24.6 GB, IQ2_XXS is 28.6 GB, IQ2_XS is 31.8 GB, IQ2_S is 32.3 GB, IQ2_M is 35.5 GB and 7 more.

What context length does Llama 4 Scout 17B 16E Instruct support?

The GGUF header lists a trained context length of 10,485,760 tokens (10240K). The KV cache grows with the context you use: about 1.6 GB at 8K and 6.4 GB at 32K.

Where can I download Llama 4 Scout 17B 16E Instruct GGUF?

The files are on Hugging Face in the mradermacher/Llama-4-Scout-17B-16E-Instruct-i1-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Llama 4 Scout 17B 16E Instruct use?

Hugging Face lists the license as other. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Can I run this model on 8 GB VRAM?

The smallest quant IQ1_S requires about 24.3 GB VRAM at 8k context, so 8 GB VRAM is insufficient.

Does this model support vision tasks?

The GGUF files do not include mmproj files, so vision is not supported in this release.

What license applies to this model?

The model is released under an other license; check the Hugging Face page for details.

Other GGUFs of Llama-4-Scout-17B-16E-Instruct

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Llama models

All Llama →

Other large models

All large models →