LL

afx issue llama model

LlamaGGUF by nikinetrahutamaUpdated 2023-12-14
Download on Hugging Face
Parameters13B
Context2K
Layers32
Architecturellama
Smallest quant4.2 GB
Quick answer

afx issue llama model needs about 12.9 GB of memory at Q4_1 (a 8.1 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 3 quants, from 4.2 GB (Q4_1) to 8.1 GB (Q4_1).

afx issue llama model is a 13B-parameter Llama model in GGUF format, quantized by nikinetrahutama. Its trained context length is 2K tokens. The repository has 3 quant files, from 4.2 GB (Q4_1) to 8.1 GB (Q4_1).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_14.2 GB 5.8 GB
Fits Get file →
Q4_18.1 GB 9.7 GB
Too big Get file →
Q4_18.1 GB 9.7 GB
Too big Get file →

What GPU do you need for afx issue llama model?

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_1 (4.2 GB file, about 9.0 GB in use).
  • 16 GB VRAM: the best quant that fits is Q4_1 (8.1 GB file, about 12.9 GB in use).

Which afx issue llama model quant should you choose?

Q4_1 (8.1 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.

If memory is tight, the smallest file is Q4_1 at 4.2 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
Parameters13B
Layers32
Trained context2,048 tokens
KV cache (fp16)512 KB per token

Source

Quantized bynikinetrahutama
FamilyLlama
Downloads (HF)39
Last updated2023-12-14

Frequently asked questions about afx issue llama model

How much VRAM does afx issue llama model need?

About 12.9 GB at Q4_1 with an 8K context window. That is the 8.1 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 afx issue llama model 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 afx issue llama model GGUF?

It depends on the quant: Q4_1 is 4.2 GB, Q4_1 is 8.1 GB, Q4_1 is 8.1 GB.

What context length does afx issue llama model support?

The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 4.3 GB at 8K and 1.1 GB at 2K.

Where can I download afx issue llama model GGUF?

The files are on Hugging Face in the nikinetrahutama/afx-issue-llama-model 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 nikinetrahutama

All by nikinetrahutama →

More Llama models

All Llama →

Other medium models

All medium models →