LL

Llama 3.3 Swallow 70B Instruct v0.4

LlamaGGUF by yasu-ohUpdated 2025-03-11
Download on Hugging Face
Parameters70.6B
Context128K
Layers80
Architecturellama
Smallest quant37.9 GB
Quick answer

Llama 3.3 Swallow 70B Instruct v0.4 needs about 41.1 GB of memory at IQ4_XS (a 37.9 GB file) with an 8K context window, so it fits on a 48 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 10.7 GB.

Llama 3.3 Swallow 70B Instruct v0.4 is a 70.6B-parameter Llama model in GGUF format, quantized by yasu-oh. Its trained context length is 128K tokens. The repository has 1 quant file, from 37.9 GB (IQ4_XS) to 37.9 GB (IQ4_XS).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ4_XS37.9 GB 41.1 GB
Too big Get file →

What GPU do you need for Llama 3.3 Swallow 70B Instruct v0.4?

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 IQ4_XS (37.9 GB file, about 41.1 GB in use).

Which Llama 3.3 Swallow 70B Instruct v0.4 quant should you choose?

IQ4_XS (37.9 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters70.6B
Layers80
Trained context131,072 tokens
KV cache (fp16)320 KB per token

Source

Quantized byyasu-oh
FamilyLlama
Licensellama3.3
Downloads (HF)9
Last updated2025-03-11

Frequently asked questions about Llama 3.3 Swallow 70B Instruct v0.4

How much VRAM does Llama 3.3 Swallow 70B Instruct v0.4 need?

About 41.1 GB at IQ4_XS with an 8K context window. That is the 37.9 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 3.3 Swallow 70B Instruct v0.4 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 41.1 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Llama 3.3 Swallow 70B Instruct v0.4 GGUF?

It depends on the quant: IQ4_XS is 37.9 GB.

What context length does Llama 3.3 Swallow 70B Instruct v0.4 support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 2.7 GB at 8K and 10.7 GB at 32K.

Where can I download Llama 3.3 Swallow 70B Instruct v0.4 GGUF?

The files are on Hugging Face in the yasu-oh/Llama-3.3-Swallow-70B-Instruct-v0.4-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 3.3 Swallow 70B Instruct v0.4 use?

Hugging Face lists the license as llama3.3. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Other GGUFs of Llama-3.3-Swallow-70B-Instruct-v0.4

Similar models

Browse all →

More from yasu-oh

All by yasu-oh →

More Llama models

All Llama →

Other large models

All large models →