LL

persian llama 7b GGUF Q4

LlamaGGUF by mostafaamiriUpdated 2024-01-13
Download on Hugging Face
Parameters6.9B
Context4K
Layers32
Architecturellama
Smallest quant4.2 GB
Quick answer

persian llama 7b GGUF Q4 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 2 quants, from 4.2 GB (Q4_K_M) to 7.3 GB (Q8_K_M).

persian llama 7b GGUF Q4 is a 6.9B-parameter Llama model in GGUF format, quantized by mostafaamiri. Its trained context length is 4K tokens. The repository has 2 quant files, from 4.2 GB (Q4_K_M) to 7.3 GB (Q8_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M4.2 GB 6.8 GB
Fits Get file →
Q8_K_M7.3 GB 10.0 GB
Too big Get file →

What GPU do you need for persian llama 7b GGUF Q4?

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 Q4_K_M (4.2 GB file, about 9.0 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_K_M (7.3 GB file, about 12.1 GB in use).

Which persian llama 7b GGUF Q4 quant should you choose?

Q4_K_M is the usual starting point for persian llama 7b GGUF Q4: it balances file size and quality well. Here it is a 4.2 GB file.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters6.9B
Layers32
Trained context4,096 tokens
KV cache (fp16)512 KB per token

Source

Quantized bymostafaamiri
FamilyLlama
Licensebsd
Downloads (HF)65
Last updated2024-01-13

Frequently asked questions about persian llama 7b GGUF Q4

How much VRAM does persian llama 7b GGUF Q4 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 persian llama 7b GGUF Q4 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 9.0 GB, so you would need a larger GPU or CPU offloading.

What is the file size of persian llama 7b GGUF Q4 GGUF?

It depends on the quant: Q4_K_M is 4.2 GB, Q8_K_M is 7.3 GB.

What context length does persian llama 7b GGUF Q4 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 persian llama 7b GGUF Q4 GGUF?

The files are on Hugging Face in the mostafaamiri/persian-llama-7b-GGUF-Q4 repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does persian llama 7b GGUF Q4 use?

Hugging Face lists the license as bsd. 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 Llama models

All Llama →

Other small models

All small models →