LL

vietnamese llama2 7b 40GB

LlamaGGUF by BachhoangUpdated 2024-04-28
Download on Hugging Face
Parameters6.86B
Context4K
Layers32
Architecturellama
Smallest quant4.7 GB
Quick answer

vietnamese llama2 7b 40GB needs about 9.7 GB of memory at Q5_K_M (a 4.9 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 4 quants, from 4.7 GB (Q5_0) to 13.7 GB (F16).

vietnamese llama2 7b 40GB is a 6.86B-parameter Llama model in GGUF format, quantized by Bachhoang. Its trained context length is 4K tokens. The repository has 4 quant files, from 4.7 GB (Q5_0) to 13.7 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q5_04.7 GB 7.4 GB
Tight Get file →
Q5_K_M4.9 GB 7.5 GB
Tight Get file →
Q8_07.3 GB 10.0 GB
Too big Get file →
F1613.7 GB 16.4 GB
Too big Get file →

What GPU do you need for vietnamese llama2 7b 40GB?

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 Q5_K_M (4.9 GB file, about 9.7 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 (13.7 GB file, about 18.5 GB in use).

Which vietnamese llama2 7b 40GB quant should you choose?

Q5_K_M (4.9 GB) is the middle option in this repository. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.

If memory is tight, the smallest file is Q5_0 at 4.7 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
Parameters6.86B
Layers32
Trained context4,096 tokens
KV cache (fp16)512 KB per token

Source

Quantized byBachhoang
FamilyLlama
Downloads (HF)14
Last updated2024-04-28

Frequently asked questions about vietnamese llama2 7b 40GB

How much VRAM does vietnamese llama2 7b 40GB need?

About 9.7 GB at Q5_K_M with an 8K context window. That is the 4.9 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 vietnamese llama2 7b 40GB on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 9.5 GB, so you would need a larger GPU or CPU offloading.

What is the file size of vietnamese llama2 7b 40GB GGUF?

It depends on the quant: Q5_0 is 4.7 GB, Q5_K_M is 4.9 GB, Q8_0 is 7.3 GB, F16 is 13.7 GB.

What context length does vietnamese llama2 7b 40GB 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 vietnamese llama2 7b 40GB GGUF?

The files are on Hugging Face in the Bachhoang/vietnamese-llama2-7b-40GB-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 →