LL

llama 2 chat 13b

LlamaGGUF by qnixsynapseUpdated 2023-08-26
Download on Hugging Face
Parameters13B
Context4K
Layers—
Architecturellama
Smallest quant7.9 GB
Quick answer

llama 2 chat 13b needs about 9.3 GB of memory at Q4_K_M (a 7.9 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 2 quants, from 7.9 GB (Q4_K_M) to 26.0 GB (F16).

llama 2 chat 13b is a 13B-parameter Llama model in GGUF format, quantized by qnixsynapse. Its trained context length is 4K tokens. The repository has 2 quant files, from 7.9 GB (Q4_K_M) to 26.0 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M7.9 GB 8.8 GB
Too big Get file →
F1626.0 GB 28.1 GB
Too big Get file →

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

These figures add the file size, an fp16 KV cache at an 8K context window 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: the best quant that fits is Q4_K_M (7.9 GB file, about 9.3 GB in use).
  • 16 GB VRAM: the best quant that fits is Q4_K_M (7.9 GB file, about 9.3 GB in use).
  • 24 GB VRAM: the best quant that fits is Q4_K_M (7.9 GB file, about 9.3 GB in use).
  • 32 GB VRAM: the best quant that fits is F16 (26.0 GB file, about 29.7 GB in use).

Which llama 2 chat 13b quant should you choose?

Q4_K_M is the usual starting point for llama 2 chat 13b: it balances file size and quality well. Here it is a 7.9 GB file.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters13B
Trained context4,096 tokens

Source

Quantized byqnixsynapse
FamilyLlama
Licensellama2
Downloads (HF)201
Last updated2023-08-26

Frequently asked questions about llama 2 chat 13b

How much VRAM does llama 2 chat 13b need?

About 9.3 GB at Q4_K_M with an 8K context window. That is the 7.9 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 2 chat 13b on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 9.3 GB, so you would need a larger GPU or CPU offloading.

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

It depends on the quant: Q4_K_M is 7.9 GB, F16 is 26.0 GB.

What context length does llama 2 chat 13b support?

The GGUF header lists a trained context length of 4,096 tokens (4K).

Where can I download llama 2 chat 13b GGUF?

The files are on Hugging Face in the qnixsynapse/llama-2-chat-13b-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 2 chat 13b use?

Hugging Face lists the license as llama2. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Similar models

Browse all →

More from qnixsynapse

All by qnixsynapse →

More Llama models

All Llama →

Other medium models

All medium models →