LL

llama 4 scout 17b 16e it

LlamaGGUF by chatpigUpdated 2025-04-13
Download on Hugging Face
Parameters110B
Context10240K
Layers48
Architecturellama4
Smallest quant39.6 GB
Quick answer

llama 4 scout 17b 16e it needs about 59.9 GB of memory at Q3_K_L (a 57.8 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 8 quants, from 39.6 GB (Q2_K) to 113.4 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 6.4 GB.

Llama‑4 Scout 17B 16E Instruct – 110B parameters with vision support

Llama‑4 Scout 17B 16E Instruct is a 110B parameter model built on the Llama‑4 architecture. It supports vision tasks and offers multiple quantizations for different memory budgets. The model is available in GGUF format and can be run with llama.cpp.

Good at

  • Vision‑enabled text generation
  • Large context handling
  • High parameter count

Limits

  • Requires 8 k context for estimates
  • No explicit license details
  • Large memory for higher quants

Best for

  • Vision‑augmented chatbots
  • Long‑form content creation
  • Research prototyping

Who it’s for. Developers and researchers needing a large, vision‑capable LLM for local deployment. The model is suitable for those who can manage the memory requirements of the chosen quantization.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K39.6 GB (4 parts) 41.7 GB
Too big Get file →
Q3_K_S49.8 GB (5 parts) 51.9 GB
Too big Get file →
Q3_K_M54.3 GB (3 parts) 56.4 GB
Too big Get file →
Q3_K_L57.8 GB (3 parts) 59.9 GB
Too big Get file →
Q4_063.1 GB (3 parts) 65.2 GB
Too big Get file →
Q5_074.3 GB (3 parts) 76.4 GB
Too big Get file →
Q6_K88.8 GB (5 parts) 90.9 GB
Too big Get file →
Q8_0113.4 GB (4 parts) 115.5 GB
Too big Get file →

For 8 GB VRAM, use Q2_K (39.56 GB file, ~41.7 GB memory at 8 k context). For 16 GB VRAM, Q3_K_S (49.75 GB file, ~51.9 GB memory). For 32 GB VRAM, Q4_0 (63.05 GB file, ~65.2 GB memory).

What GPU do you need for llama 4 scout 17b 16e it?

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: no quant fits at an 8K context.
  • 48 GB VRAM: the best quant that fits is Q2_K (39.6 GB file, about 41.7 GB in use).

Which llama 4 scout 17b 16e it quant should you choose?

Q3_K_L (57.8 GB) is the middle option in this repository. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

If memory is tight, the smallest file is Q2_K at 39.6 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
Parameters110B (approximate, mixture of experts)
Layers48
Trained context10,485,760 tokens
KV cache (fp16)192 KB per token

Source

Quantized bychatpig
FamilyLlama
Licenseother
Downloads (HF)1,564
Last updated2025-04-13

Frequently asked questions about llama 4 scout 17b 16e it

How much VRAM does llama 4 scout 17b 16e it need?

About 59.9 GB at Q3_K_L with an 8K context window. That is the 57.8 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 it on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 41.7 GB, so you would need a larger GPU or CPU offloading.

What is the file size of llama 4 scout 17b 16e it GGUF?

It depends on the quant: Q2_K is 39.6 GB, Q3_K_S is 49.8 GB, Q3_K_M is 54.3 GB, Q3_K_L is 57.8 GB, Q4_0 is 63.1 GB, Q5_0 is 74.3 GB and 2 more.

What context length does llama 4 scout 17b 16e it 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 it GGUF?

The files are on Hugging Face in the chatpig/llama-4-scout-17b-16e-it-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 it 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?

Yes, using the Q2_K quantization which requires about 41.7 GB of memory at 8 k context, but you need a system with sufficient RAM to load the model.

Does the model support image input?

Yes, the model has detected vision abilities and can process image data when used with compatible front‑ends.

How many shards are needed for the Q3_K_M quant?

The Q3_K_M quant is split into 3 shards, each part must be downloaded and merged before use.

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

Similar models

Browse all →

More from chatpig

All by chatpig →

More Llama models

All Llama →

Other large models

All large models →