LL

limarp llama2 mergetest

LlamaGGUF by actionpaceUpdated 2023-11-13
Download on Hugging Face
Parameters13B
Context4K
Layers40
Architecturellama
Smallest quant9.2 GB
Quick answer

limarp llama2 mergetest needs about 16.4 GB of memory at Q5_K_M (a 9.2 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 2 quants, from 9.2 GB (Q5_K_M) to 13.8 GB (Q8_0).

limarp llama2 mergetest is a 13B-parameter Llama model in GGUF format, quantized by actionpace. Its trained context length is 4K tokens. The repository has 2 quant files, from 9.2 GB (Q5_K_M) to 13.8 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q5_K_M9.2 GB 13.1 GB
Too big Get file →
Q8_013.8 GB 17.7 GB
Too big Get file →

What GPU do you need for limarp llama2 mergetest?

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 (13.8 GB file, about 21.0 GB in use).

Which limarp llama2 mergetest quant should you choose?

Q5_K_M (9.2 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.

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 byactionpace
FamilyLlama
Downloads (HF)17
Last updated2023-11-13

Frequently asked questions about limarp llama2 mergetest

How much VRAM does limarp llama2 mergetest need?

About 16.4 GB at Q5_K_M with an 8K context window. That is the 9.2 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 limarp llama2 mergetest on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 16.4 GB, so you would need a larger GPU or CPU offloading.

What is the file size of limarp llama2 mergetest GGUF?

It depends on the quant: Q5_K_M is 9.2 GB, Q8_0 is 13.8 GB.

What context length does limarp llama2 mergetest 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 limarp llama2 mergetest GGUF?

The files are on Hugging Face in the actionpace/limarp-llama2-mergetest 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 actionpace

All by actionpace →

More Llama models

All Llama →

Other medium models

All medium models →