LL

llama3 70B quantized

LlamaGGUF by fxinwei123Updated 2025-02-10
Download on Hugging Face
Parameters70.6B
Context128K
Layers80
Architecturellama
Smallest quant38.3 GB
Quick answer

llama3 70B quantized needs about 45.7 GB of memory at its main file (a 42.5 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 8 quants, from 38.3 GB (IQ4_XS) to 49.9 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 10.7 GB.

llama3 70B quantized is a 70.6B-parameter Llama model in GGUF format, quantized by fxinwei123. Its trained context length is 128K tokens. The repository has 8 quant files, from 38.3 GB (IQ4_XS) to 49.9 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ4_XS38.3 GB 41.5 GB
Too big Get file →
—42.5 GB 45.7 GB
Too big Get file →
—42.5 GB 45.7 GB
Too big Get file →
—42.5 GB 45.7 GB
Too big Get file →
—42.5 GB 45.7 GB
Too big Get file →
—42.5 GB 45.7 GB
Too big Get file →
—42.5 GB 45.7 GB
Too big Get file →
—49.9 GB 53.1 GB
Too big Get file →

What GPU do you need for llama3 70B quantized?

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 the main file (42.5 GB file, about 45.7 GB in use).

Which llama3 70B quantized quant should you choose?

If memory is tight, the smallest file is IQ4_XS at 38.3 GB, with the quality trade-offs that come with fewer bits. 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 byfxinwei123
FamilyLlama
Downloads (HF)45
Last updated2025-02-10

Frequently asked questions about llama3 70B quantized

How much VRAM does llama3 70B quantized need?

About 45.7 GB at its main file with an 8K context window. That is the 42.5 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 llama3 70B quantized on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 41.5 GB, so you would need a larger GPU or CPU offloading.

What is the file size of llama3 70B quantized GGUF?

It depends on the quant: IQ4_XS is 38.3 GB, file is 42.5 GB, file is 42.5 GB, file is 42.5 GB, file is 42.5 GB, file is 42.5 GB and 2 more.

What context length does llama3 70B quantized 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 llama3 70B quantized GGUF?

The files are on Hugging Face in the fxinwei123/llama3-70B-quantized repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Similar models

Browse all →

More from fxinwei123

All by fxinwei123 →

More Llama models

All Llama →

Other large models

All large models →