LL

elinas/Llama-3-15B-Instruct-zeroed

LlamaGGUF by featherless-ai-quantsUpdated 2024-11-10
Download on Hugging Face
Parameters15B
Context8K
Layers64
Architecturellama
Smallest quant5.7 GB
Quick answer

elinas/Llama-3-15B-Instruct-zeroed needs about 11.8 GB of memory at Q4_K_M (a 9.1 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 11 quants, from 5.7 GB (Q2_K) to 16.0 GB (Q8_0).

elinas/Llama-3-15B-Instruct-zeroed is a 15B-parameter Llama model in GGUF format, quantized by featherless-ai-quants. Its trained context length is 8K tokens. The repository has 11 quant files, from 5.7 GB (Q2_K) to 16.0 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K5.7 GB 8.4 GB
Too big Get file →
Q3_K_S6.7 GB 9.3 GB
Too big Get file →
Q3_K_M7.4 GB 10.0 GB
Too big Get file →
Q3_K_L8.0 GB 10.6 GB
Too big Get file →
IQ4_XS8.3 GB 10.9 GB
Too big Get file →
Q4_K_S8.6 GB 11.3 GB
Too big Get file →
Q4_K_M9.1 GB 11.8 GB
Too big Get file →
Q5_K_S10.4 GB 13.0 GB
Too big Get file →
Q5_K_M10.7 GB 13.3 GB
Too big Get file →
Q6_K12.3 GB 15.0 GB
Too big Get file →
Q8_016.0 GB 18.6 GB
Too big Get file →

What GPU do you need for elinas/Llama-3-15B-Instruct-zeroed?

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 (9.1 GB file, about 11.8 GB in use).
  • 16 GB VRAM: the best quant that fits is Q6_K (12.3 GB file, about 15.0 GB in use).
  • 24 GB VRAM: the best quant that fits is Q8_0 (16.0 GB file, about 18.6 GB in use).

Which elinas/Llama-3-15B-Instruct-zeroed quant should you choose?

Q4_K_M is the usual starting point for elinas/Llama-3-15B-Instruct-zeroed: it balances file size and quality well. Here it is a 9.1 GB file.

The Q8_0 file is 16.0 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 Q2_K at 5.7 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters15B
Layers64
Trained context8,192 tokens
KV cache (fp16)256 KB per token

Source

FamilyLlama
Licensellama3
Downloads (HF)157
Last updated2024-11-10

Frequently asked questions about elinas/Llama-3-15B-Instruct-zeroed

How much VRAM does elinas/Llama-3-15B-Instruct-zeroed need?

About 11.8 GB at Q4_K_M with an 8K context window. That is the 9.1 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 elinas/Llama-3-15B-Instruct-zeroed on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 8.4 GB, so you would need a larger GPU or CPU offloading.

What is the file size of elinas/Llama-3-15B-Instruct-zeroed GGUF?

It depends on the quant: Q2_K is 5.7 GB, Q3_K_S is 6.7 GB, Q3_K_M is 7.4 GB, Q3_K_L is 8.0 GB, IQ4_XS is 8.3 GB, Q4_K_S is 8.6 GB and 5 more.

What context length does elinas/Llama-3-15B-Instruct-zeroed support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 2.1 GB at 8K and 2.1 GB at 8K.

Where can I download elinas/Llama-3-15B-Instruct-zeroed GGUF?

The files are on Hugging Face in the featherless-ai-quants/elinas-Llama-3-15B-Instruct-zeroed-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 elinas/Llama-3-15B-Instruct-zeroed 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 Llama-3-15B-Instruct-zeroed

Similar models

Browse all →

More from featherless-ai-quants

All by featherless-ai-quants →

More Llama models

All Llama →

Other medium models

All medium models →