LL

vdb llama2 7B

LlamaGGUF by BachhoangUpdated 2024-04-23
Download on Hugging Face
Parameters6.88B
Context4K
Layers32
Architecturellama
Smallest quant3.9 GB
Quick answer

vdb llama2 7B needs about 9.0 GB of memory at Q4_K_M (a 4.2 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 7 quants, from 3.9 GB (Q4_0) to 13.8 GB (F16).

vdb llama2 7B is a 6.88B-parameter Llama model in GGUF format, quantized by Bachhoang. Its trained context length is 4K tokens. The repository has 7 quant files, from 3.9 GB (Q4_0) to 13.8 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_03.9 GB 6.6 GB
Fits Get file →
Q4_K_M4.2 GB 6.8 GB
Fits Get file →
Q5_04.8 GB 7.4 GB
Tight Get file →
Q5_K_M4.9 GB 7.5 GB
Tight Get file →
Q6_K5.6 GB 8.3 GB
Too big Get file →
Q8_07.3 GB 10.0 GB
Too big Get file →
F1613.8 GB 16.4 GB
Too big Get file →

What GPU do you need for vdb llama2 7B?

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: the best quant that fits is Q6_K (5.6 GB file, about 10.4 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (7.3 GB file, about 12.1 GB in use).
  • 24 GB VRAM: the best quant that fits is F16 (13.8 GB file, about 18.6 GB in use).

Which vdb llama2 7B quant should you choose?

Q4_K_M is the usual starting point for vdb llama2 7B: it balances file size and quality well. Here it is a 4.2 GB file.

The Q8_0 file is 7.3 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is Q4_0 at 3.9 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
Parameters6.88B
Layers32
Trained context4,096 tokens
KV cache (fp16)512 KB per token

Source

Quantized byBachhoang
FamilyLlama
Downloads (HF)22
Last updated2024-04-23

Frequently asked questions about vdb llama2 7B

How much VRAM does vdb llama2 7B need?

About 9.0 GB at Q4_K_M with an 8K context window. That is the 4.2 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 vdb llama2 7B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 8.7 GB, so you would need a larger GPU or CPU offloading.

What is the file size of vdb llama2 7B GGUF?

It depends on the quant: Q4_0 is 3.9 GB, Q4_K_M is 4.2 GB, Q5_0 is 4.8 GB, Q5_K_M is 4.9 GB, Q6_K is 5.6 GB, Q8_0 is 7.3 GB and 1 more.

What context length does vdb llama2 7B support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 4.3 GB at 8K and 2.1 GB at 4K.

Where can I download vdb llama2 7B GGUF?

The files are on Hugging Face in the Bachhoang/vdb-llama2-7B-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 Bachhoang

All by Bachhoang →

More Llama models

All Llama →

Other small models

All small models →