LL

lIlBrother llama2 merge v0.1

LlamaGGUF by RichardErkhovUpdated 2024-08-27
Download on Hugging Face
Parameters13.2B
Context2K
Layers40
Architecturellama
Smallest quant1.4 GB
Quick answer

lIlBrother llama2 merge v0.1 needs about 15.2 GB of memory at Q4_K_M (a 8.0 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 22 quants, from 1.4 GB (Q5_K) to 14.0 GB (Q8_0).

lIlBrother llama2 merge v0.1 is a 13.2B-parameter Llama model in GGUF format, quantized by RichardErkhov. Its trained context length is 2K tokens. The repository has 22 quant files, from 1.4 GB (Q5_K) to 14.0 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q5_K1.4 GB 3.5 GB
Fits Get file →
Q5_K_S4.4 GB 6.5 GB
Fits Get file →
Q2_K4.9 GB 7.1 GB
Fits Get file →
IQ3_XS5.5 GB 7.6 GB
Tight Get file →
IQ3_S5.8 GB 7.9 GB
Tight Get file →
Q3_K_S5.8 GB 7.9 GB
Tight Get file →
IQ3_M6.1 GB 8.3 GB
Too big Get file →
Q3_K6.4 GB 8.6 GB
Too big Get file →
Q3_K_M6.4 GB 8.6 GB
Too big Get file →
Q3_K_L7.0 GB 9.2 GB
Too big Get file →
IQ4_XS7.1 GB 9.3 GB
Too big Get file →
Q4_07.5 GB 9.6 GB
Too big Get file →
IQ4_NL7.5 GB 9.7 GB
Too big Get file →
Q4_K_S7.5 GB 9.7 GB
Too big Get file →
Q4_K8.0 GB 10.1 GB
Too big Get file →
Q4_K_M8.0 GB 10.1 GB
Too big Get file →
Q4_18.3 GB 10.5 GB
Too big Get file →
Q5_09.1 GB 11.3 GB
Too big Get file →
Q5_K_M9.3 GB 11.5 GB
Too big Get file →
Q5_19.9 GB 12.1 GB
Too big Get file →
Q6_K10.8 GB 13.0 GB
Too big Get file →
Q8_014.0 GB 16.2 GB
Too big Get file →

What GPU do you need for lIlBrother llama2 merge v0.1?

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_S (4.4 GB file, about 11.6 GB in use).
  • 16 GB VRAM: the best quant that fits is Q4_1 (8.3 GB file, about 15.5 GB in use).
  • 24 GB VRAM: the best quant that fits is Q8_0 (14.0 GB file, about 21.2 GB in use).

Which lIlBrother llama2 merge v0.1 quant should you choose?

Q4_K_M is the usual starting point for lIlBrother llama2 merge v0.1: it balances file size and quality well. Here it is a 8.0 GB file.

The Q8_0 file is 14.0 GB, about 1.8 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 Q5_K at 1.4 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
Parameters13.2B
Layers40
Trained context2,048 tokens
KV cache (fp16)800 KB per token

Source

Quantized byRichardErkhov
FamilyLlama
Downloads (HF)6
Last updated2024-08-27

Frequently asked questions about lIlBrother llama2 merge v0.1

How much VRAM does lIlBrother llama2 merge v0.1 need?

About 15.2 GB at Q4_K_M with an 8K context window. That is the 8.0 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 lIlBrother llama2 merge v0.1 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 8.6 GB, so you would need a larger GPU or CPU offloading.

What is the file size of lIlBrother llama2 merge v0.1 GGUF?

It depends on the quant: Q5_K is 1.4 GB, Q5_K_S is 4.4 GB, Q2_K is 4.9 GB, IQ3_XS is 5.5 GB, IQ3_S is 5.8 GB, Q3_K_S is 5.8 GB and 16 more.

What context length does lIlBrother llama2 merge v0.1 support?

The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 6.7 GB at 8K and 1.7 GB at 2K.

Where can I download lIlBrother llama2 merge v0.1 GGUF?

The files are on Hugging Face in the RichardErkhov/lIlBrother_-_llama2-merge-v0.1-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 RichardErkhov

All by RichardErkhov →

More Llama models

All Llama →

Other medium models

All medium models →