LL

H2Ogpt 4096 Llama2 13b Chat

LlamaGGUF by ZeroWwUpdated 2024-07-21
Download on Hugging Face
Parameters13B
Context4K
Layers40
Architecturellama
Smallest quant9.6 GB
Quick answer

H2Ogpt 4096 Llama2 13b Chat needs about 21.0 GB of memory at its main file (a 13.8 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 5 quants, from 9.6 GB (Q5_K) to 26.0 GB (F16).

H2Ogpt 4096 Llama2 13b Chat is a 13B-parameter Llama model in GGUF format, quantized by ZeroWw. Its trained context length is 4K tokens. The repository has 5 quant files, from 9.6 GB (Q5_K) to 26.0 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q5_K9.6 GB 13.5 GB
Too big Get file →
Q6_K11.1 GB 14.9 GB
Too big Get file →
—13.8 GB 17.7 GB
Too big Get file →
Q8_014.1 GB 18.0 GB
Too big Get file →
F1626.0 GB 29.9 GB
Too big Get file →

What GPU do you need for H2Ogpt 4096 Llama2 13b Chat?

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 (14.1 GB file, about 21.3 GB in use).
  • 32 GB VRAM: the best quant that fits is Q8_0 (14.1 GB file, about 21.3 GB in use).
  • 48 GB VRAM: the best quant that fits is F16 (26.0 GB file, about 33.2 GB in use).

Which H2Ogpt 4096 Llama2 13b Chat quant should you choose?

If memory is tight, the smallest file is Q5_K at 9.6 GB, with the quality trade-offs that come with fewer bits. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.

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 byZeroWw
FamilyLlama
Licensemit
Downloads (HF)22
Last updated2024-07-21

Frequently asked questions about H2Ogpt 4096 Llama2 13b Chat

How much VRAM does H2Ogpt 4096 Llama2 13b Chat need?

About 21.0 GB at its main file 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 H2Ogpt 4096 Llama2 13b Chat on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 16.8 GB, so you would need a larger GPU or CPU offloading.

What is the file size of H2Ogpt 4096 Llama2 13b Chat GGUF?

It depends on the quant: Q5_K is 9.6 GB, Q6_K is 11.1 GB, file is 13.8 GB, Q8_0 is 14.1 GB, F16 is 26.0 GB.

What context length does H2Ogpt 4096 Llama2 13b Chat 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 H2Ogpt 4096 Llama2 13b Chat GGUF?

The files are on Hugging Face in the ZeroWw/h2ogpt-4096-llama2-13b-chat-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 H2Ogpt 4096 Llama2 13b Chat use?

Hugging Face lists the license as mit. 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 ZeroWw

All by ZeroWw →

More Llama models

All Llama →

Other medium models

All medium models →