LL

llamagnific 3 87b

LlamaGGUF by nistenUpdated 2024-07-17
Download on Hugging Face
Parameters86.8B
Context8K
Layers99
Architecturellama
Smallest quant24.5 GB
Quick answer

llamagnific 3 87b needs about 53.5 GB of memory at Q4_K_S (a 49.7 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 8 quants, from 24.5 GB to 173.6 GB (BF16).

llamagnific 3 87b is a 86.8B-parameter Llama model in GGUF format, quantized by nisten. Its trained context length is 8K tokens. The repository has 8 quant files, from 24.5 GB to 173.6 GB (BF16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—24.5 GB 28.3 GB
Too big Get file →
—47.4 GB 51.2 GB
Too big Get file →
—49.2 GB 53.0 GB
Too big Get file →
Q4_K_S49.7 GB 53.5 GB
Too big Get file →
Q4_K_L53.0 GB (2 parts) 56.8 GB
Too big Get file →
Q5_K_M62.1 GB (2 parts) 65.9 GB
Too big Get file →
—92.2 GB (2 parts) 96.1 GB
Too big Get file →
BF16173.6 GB (4 parts) 177.5 GB
Too big Get file →

What GPU do you need for llamagnific 3 87b?

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: no quant fits at an 8K context.
  • 32 GB VRAM: the best quant that fits is the main file (24.5 GB file, about 28.3 GB in use).
  • 48 GB VRAM: the best quant that fits is the main file (24.5 GB file, about 28.3 GB in use).

Which llamagnific 3 87b quant should you choose?

Q4_K_S (49.7 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 the first one in the table at 24.5 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters86.8B
Layers99
Trained context8,192 tokens
KV cache (fp16)396 KB per token

Source

Quantized bynisten
FamilyLlama
Licensellama3
Downloads (HF)278
Last updated2024-07-17

Frequently asked questions about llamagnific 3 87b

How much VRAM does llamagnific 3 87b need?

About 53.5 GB at Q4_K_S with an 8K context window. That is the 49.7 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 llamagnific 3 87b on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 28.3 GB, so you would need a larger GPU or CPU offloading.

What is the file size of llamagnific 3 87b GGUF?

It depends on the quant: file is 24.5 GB, file is 47.4 GB, file is 49.2 GB, Q4_K_S is 49.7 GB, Q4_K_L is 53.0 GB, Q5_K_M is 62.1 GB and 2 more.

What context length does llamagnific 3 87b support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 3.3 GB at 8K and 3.3 GB at 8K.

Where can I download llamagnific 3 87b GGUF?

The files are on Hugging Face in the nisten/llamagnific-3-87b-gguf repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does llamagnific 3 87b use?

Hugging Face lists the license as llama3. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Other GGUFs of llamagnific-3-87b

Similar models

Browse all →

More from nisten

All by nisten →

More Llama models

All Llama →

Other large models

All large models →