LL

Llama-4-Scout-17B-16E-Instruct

LlamaGGUF by unslothUpdated 2025-06-17
Download on Hugging Face
Parameters108B
Context10240K
Layers48
Architecturellama4
Smallest quant29.3 GB
Quick answer

Llama-4-Scout-17B-16E-Instruct needs about 67.5 GB of memory at Q4_K_M (a 65.4 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 27 quants, from 29.3 GB (TQ1_0) to 215.6 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 6.4 GB.

17B Llama‑4 Scout with 16 experts, multimodal, 10M context length

Llama‑4 Scout is a 17‑billion‑parameter model with 16 experts. It supports multilingual text and image input and produces multilingual text and code. The model is trained on a mix of public and Meta data and has a maximum context length of 10 million tokens.

Good at

  • Multimodal text and image understanding
  • Large context handling
  • Mixture‑of‑experts efficiency

Limits

  • No vision support in current GGUF version
  • Large VRAM required for higher‑bit quants
  • License type not specified

Best for

  • Chatbots needing long context
  • Multilingual content generation
  • Image‑to‑text tasks

Who it’s for. Developers building applications that require extensive context and multimodal input. Suitable for teams with GPU resources to run large‑bit quantizations.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
TQ1_029.3 GB 31.4 GB
Too big Get file →
IQ1_S32.5 GB 34.6 GB
Too big Get file →
IQ1_M35.0 GB 37.1 GB
Too big Get file →
IQ2_XXS37.4 GB 39.5 GB
Too big Get file →
IQ2_M39.1 GB 41.2 GB
Too big Get file →
Q2_K39.6 GB 41.7 GB
Too big Get file →
Q2_K_L39.8 GB 41.9 GB
Too big Get file →
Q2_K_XL42.4 GB 44.5 GB
Too big Get file →
IQ3_XXS45.7 GB 47.8 GB
Too big Get file →
Q3_K_S46.7 GB 48.9 GB
Too big Get file →
Q3_K_XL49.0 GB 51.1 GB
Too big Get file →
Q3_K_M51.8 GB (2 parts) 53.9 GB
Too big Get file →
IQ4_XS57.7 GB (2 parts) 59.8 GB
Too big Get file →
IQ4_NL60.9 GB (2 parts) 63.1 GB
Too big Get file →
Q4_061.2 GB (2 parts) 63.3 GB
Too big Get file →
Q4_K_S61.5 GB (2 parts) 63.6 GB
Too big Get file →
Q4_K_XL62.0 GB (2 parts) 64.1 GB
Too big Get file →
Q4_K_M65.4 GB (2 parts) 67.5 GB
Too big Get file →
Q4_167.6 GB (2 parts) 69.7 GB
Too big Get file →
Q5_K_S74.3 GB (2 parts) 76.4 GB
Too big Get file →
Q5_K_M76.5 GB (2 parts) 78.7 GB
Too big Get file →
Q5_K_XL79.1 GB (2 parts) 81.3 GB
Too big Get file →
Q6_K88.4 GB (2 parts) 90.5 GB
Too big Get file →
Q6_K_XL94.1 GB (2 parts) 96.2 GB
Too big Get file →
Q8_0114.5 GB (3 parts) 116.6 GB
Too big Get file →
Q8_K_XL128.2 GB (3 parts) 130.3 GB
Too big Get file →
BF16215.6 GB (5 parts) 217.7 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_S (≈63.6 GB memory at 8k context). For 16 GB VRAM, Q4_K_M (≈67.5 GB) or Q4_K_XL (≈64.1 GB). Higher‑bit quants like Q8_0 need 90 GB VRAM or more.

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 TQ1_0 (29.3 GB file, about 31.4 GB in use).
  • 48 GB VRAM: the best quant that fits is IQ3_XXS (45.7 GB file, about 47.8 GB in use).

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

Q4_K_M is the usual starting point for Llama-4-Scout-17B-16E-Instruct: it balances file size and quality well. Here it is a 65.4 GB file.

The Q8_0 file is 114.5 GB, about 1.8 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is TQ1_0 at 29.3 GB, with the quality trade-offs that come with fewer bits. Lower bit counts mean smaller files and more quality loss.

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 byunsloth
FamilyLlama
Licenseother
Downloads (HF)40,986
Last updated2025-06-17

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

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

About 67.5 GB at Q4_K_M with an 8K context window. That is the 65.4 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 31.4 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: TQ1_0 is 29.3 GB, IQ1_S is 32.5 GB, IQ1_M is 35.0 GB, IQ2_XXS is 37.4 GB, IQ2_M is 39.1 GB, Q2_K is 39.6 GB and 21 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 unsloth/Llama-4-Scout-17B-16E-Instruct-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 Llama‑4 Scout on 8 GB VRAM?

Only the lowest‑bit quants such as Q4_K_S are feasible, but memory usage is still high and may exceed 8 GB.

Does this model support image input?

Yes, the model is multimodal and accepts image input, but the current GGUF files are text‑only.

What context length can I use?

The model supports up to 10 million tokens, but practical usage depends on GPU memory and quantization.

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

Similar models

Browse all →

More from unsloth

All by unsloth →

More Llama models

All Llama →

Other large models

All large models →