LL

opus v1.4 70b llama3

LlamaGGUF by dreamgenUpdated 2024-06-19
Download on Hugging Face
Parameters70.6B
Context8K
Layers80
Architecturellama
Smallest quant19.1 GB
Quick answer

opus v1.4 70b llama3 needs about 45.7 GB of memory at Q4_K_M (a 42.5 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 10 quants, from 19.1 GB (IQ2_XXS) to 49.9 GB (Q5_K_M).

opus v1.4 70b llama3 is a 70.6B-parameter Llama model in GGUF format, quantized by dreamgen. Its trained context length is 8K tokens. The repository has 10 quant files, from 19.1 GB (IQ2_XXS) to 49.9 GB (Q5_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ2_XXS19.1 GB 22.3 GB
Too big Get file →
IQ2_XS21.1 GB 24.3 GB
Too big Get file →
IQ2_S22.2 GB 25.4 GB
Too big Get file →
IQ2_M24.1 GB 27.3 GB
Too big Get file →
IQ3_XS29.3 GB 32.5 GB
Too big Get file →
IQ3_S30.9 GB 34.1 GB
Too big Get file →
IQ3_M31.9 GB 35.1 GB
Too big Get file →
Q4_K_S40.3 GB 43.5 GB
Too big Get file →
Q4_K_M42.5 GB 45.7 GB
Too big Get file →
Q5_K_M49.9 GB 53.1 GB
Too big Get file →

What GPU do you need for opus v1.4 70b llama3?

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 IQ2_XXS (19.1 GB file, about 22.3 GB in use).
  • 32 GB VRAM: the best quant that fits is IQ2_M (24.1 GB file, about 27.3 GB in use).
  • 48 GB VRAM: the best quant that fits is Q4_K_M (42.5 GB file, about 45.7 GB in use).

Which opus v1.4 70b llama3 quant should you choose?

Q4_K_M is the usual starting point for opus v1.4 70b llama3: it balances file size and quality well. Here it is a 42.5 GB file.

If memory is tight, the smallest file is IQ2_XXS at 19.1 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
Parameters70.6B
Layers80
Trained context8,192 tokens
KV cache (fp16)320 KB per token

Source

Quantized bydreamgen
FamilyLlama
Downloads (HF)185
Last updated2024-06-19

Frequently asked questions about opus v1.4 70b llama3

How much VRAM does opus v1.4 70b llama3 need?

About 45.7 GB at Q4_K_M with an 8K context window. That is the 42.5 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 opus v1.4 70b llama3 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 22.3 GB, so you would need a larger GPU or CPU offloading.

What is the file size of opus v1.4 70b llama3 GGUF?

It depends on the quant: IQ2_XXS is 19.1 GB, IQ2_XS is 21.1 GB, IQ2_S is 22.2 GB, IQ2_M is 24.1 GB, IQ3_XS is 29.3 GB, IQ3_S is 30.9 GB and 4 more.

What context length does opus v1.4 70b llama3 support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 2.7 GB at 8K and 2.7 GB at 8K.

Where can I download opus v1.4 70b llama3 GGUF?

The files are on Hugging Face in the dreamgen/opus-v1.4-70b-llama3-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 opus v1.4 70b llama3 use?

Hugging Face lists the license as cc-by-nc-nd-4.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Similar models

Browse all →

More from dreamgen

All by dreamgen →

More Llama models

All Llama →

Other large models

All large models →