LL

llama 2 13b chat hf

LlamaGGUF by underfeed6415Updated 2024-02-21
Download on Hugging Face
Parameters13B
Context4K
Layers40
Architecturellama
Smallest quant13.8 GB
Quick answer

llama 2 13b chat hf needs about 21.0 GB of memory at Q8_0 (a 13.8 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 2 quants, from 13.8 GB (Q8_0) to 26.0 GB.

llama 2 13b chat hf is a 13B-parameter Llama model in GGUF format, quantized by underfeed6415. Its trained context length is 4K tokens. The repository has 2 quant files, from 13.8 GB (Q8_0) to 26.0 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q8_013.8 GB 17.7 GB
Too big Get file →
—26.0 GB 29.9 GB
Too big Get file →

What GPU do you need for llama 2 13b chat hf?

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: the best quant that fits is Q8_0 (13.8 GB file, about 21.0 GB in use).
  • 32 GB VRAM: the best quant that fits is Q8_0 (13.8 GB file, about 21.0 GB in use).
  • 48 GB VRAM: the best quant that fits is the main file (26.0 GB file, about 33.2 GB in use).

Which llama 2 13b chat hf quant should you choose?

Q8_0 (13.8 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters13B
Layers40
Trained context4,096 tokens
KV cache (fp16)800 KB per token

Source

Quantized byunderfeed6415
FamilyLlama
Downloads (HF)13
Last updated2024-02-21

Frequently asked questions about llama 2 13b chat hf

How much VRAM does llama 2 13b chat hf need?

About 21.0 GB at Q8_0 with an 8K context window. That is the 13.8 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 2 13b chat hf on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 21.0 GB, so you would need a larger GPU or CPU offloading.

What is the file size of llama 2 13b chat hf GGUF?

It depends on the quant: Q8_0 is 13.8 GB, file is 26.0 GB.

What context length does llama 2 13b chat hf support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 6.7 GB at 8K and 3.4 GB at 4K.

Where can I download llama 2 13b chat hf GGUF?

The files are on Hugging Face in the underfeed6415/llama-2-13b-chat-hf-gguf 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 underfeed6415

All by underfeed6415 →

More Llama models

All Llama →

Other medium models

All medium models →