LL

Llama 4 Scout 17B 16E Instruct 4bit

LlamaGGUF by glogwa68Updated 2025-04-07
Download on Hugging Face
Parameters17B
Context9766K
Layers48
Architecturellama
Smallest quant22.5 GB
Quick answer

Llama 4 Scout 17B 16E Instruct 4bit needs about 31.0 GB of memory at Q4_K_M (a 22.5 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 3 quants, from 22.5 GB (Q4_K_M) to 40.8 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 32.2 GB.

Llama 4 Scout 17B 16E Instruct 4bit – 17 billion parameter multimodal LLM

Llama 4 Scout is a 17 billion parameter model with 16 experts. It supports multilingual text and image input and multilingual text and code output. The model was released on April 5 2025.

Good at

  • Multilingual text generation
  • Image‑to‑text understanding
  • Code generation

Limits

  • No vision support in this quantized version
  • Requires large VRAM for full context
  • Custom commercial license

Best for

  • Chatbots needing multilingual support
  • Image captioning in supported languages
  • Code assistance for developers

Who it’s for. Developers and researchers who need a large multimodal model with multilingual capabilities and are able to comply with the custom commercial license. The model is suitable for applications that can handle the memory requirements of a 17 billion parameter LLM.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M22.5 GB 31.0 GB
Too big Get file →
Q8_028.1 GB 36.6 GB
Too big Get file →
F1640.8 GB 49.3 GB
Too big Get file →

For 8 GB VRAM use Q4_K_M (22.49 GB file, ~31 GB memory at 8 k context). For 12 GB VRAM use Q8_0 (28.09 GB file, ~36.6 GB memory). For 16 GB VRAM use F16 (40.76 GB file, ~49.3 GB memory). Memory estimates are approximate.

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

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 Q4_K_M (22.5 GB file, about 31.0 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_0 (28.1 GB file, about 36.6 GB in use).

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

Q4_K_M is the usual starting point for Llama 4 Scout 17B 16E Instruct 4bit: it balances file size and quality well. Here it is a 22.5 GB file.

The Q8_0 file is 28.1 GB, about 1.2 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.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters17B
Layers48
Trained context10,000,000 tokens
KV cache (fp16)960 KB per token

Source

Quantized byglogwa68
FamilyLlama
Licenseother
Downloads (HF)1,167
Last updated2025-04-07

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

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

About 31.0 GB at Q4_K_M with an 8K context window. That is the 22.5 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 4bit on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 31.0 GB, so you would need a larger GPU or CPU offloading.

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

It depends on the quant: Q4_K_M is 22.5 GB, Q8_0 is 28.1 GB, F16 is 40.8 GB.

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

The GGUF header lists a trained context length of 10,000,000 tokens (9766K). The KV cache grows with the context you use: about 8.1 GB at 8K and 32.2 GB at 32K.

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

The files are on Hugging Face in the glogwa68/Llama-4-scout-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 4bit 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 17B 16E Instruct 4bit on 8 GB VRAM?

The Q4_K_M quantization requires about 31 GB of VRAM at 8 k context, so 8 GB VRAM is insufficient.

Does this model support image input?

Yes, the model accepts image input but the quantized version may not expose multimodal features in all runtimes.

What license applies to this model?

It is released under a custom commercial license, the Llama 4 Community License Agreement.

Similar models

Browse all →

More from glogwa68

All by glogwa68 →

More Llama models

All Llama →

Other medium models

All medium models →