LL

AkaLlama llama3 70b v0.1

LlamaGGUF by snupilabUpdated 2024-05-08
Download on Hugging Face
Parameters70.6B
Context8K
Layers80
Architecturellama
Smallest quant9.6 GB
Quick answer

AkaLlama llama3 70b v0.1 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 12 quants, from 9.6 GB (Q6_K) to 50.0 GB (Q5_K_M).

AkaLlama llama3 70b v0.1 is a 70.6B-parameter Llama model in GGUF format, quantized by snupilab. Its trained context length is 8K tokens. The repository has 12 quant files, from 9.6 GB (Q6_K) to 50.0 GB (Q5_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q6_K9.6 GB 12.8 GB
Too big Get file →
Q2_K26.4 GB 29.6 GB
Too big Get file →
Q8_026.7 GB 29.8 GB
Too big Get file →
Q3_K_S30.9 GB 34.1 GB
Too big Get file →
Q3_K_M34.3 GB 37.5 GB
Too big Get file →
Q3_K_L37.1 GB 40.3 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 →
Q6_K48.3 GB 51.5 GB
Too big Get file →
Q8_048.3 GB 51.5 GB
Too big Get file →
Q5_K_S48.7 GB 51.8 GB
Too big Get file →
Q5_K_M50.0 GB 53.1 GB
Too big Get file →

What GPU do you need for AkaLlama llama3 70b 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: no quant fits at an 8K context.
  • 16 GB VRAM: the best quant that fits is Q6_K (9.6 GB file, about 12.8 GB in use).
  • 24 GB VRAM: the best quant that fits is Q6_K (9.6 GB file, about 12.8 GB in use).
  • 32 GB VRAM: the best quant that fits is Q8_0 (26.7 GB file, about 29.8 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 AkaLlama llama3 70b v0.1 quant should you choose?

Q4_K_M is the usual starting point for AkaLlama llama3 70b v0.1: it balances file size and quality well. Here it is a 42.5 GB file.

The Q8_0 file is 26.7 GB, about 0.6 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 Q6_K at 9.6 GB, with the quality trade-offs that come with fewer bits. Very close to the original quality for most uses, at a clearly larger size than 4-bit.

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 bysnupilab
FamilyLlama
Licenseother
Downloads (HF)498
Last updated2024-05-08

Frequently asked questions about AkaLlama llama3 70b v0.1

How much VRAM does AkaLlama llama3 70b v0.1 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 AkaLlama llama3 70b v0.1 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 12.8 GB, so you would need a larger GPU or CPU offloading.

What is the file size of AkaLlama llama3 70b v0.1 GGUF?

It depends on the quant: Q6_K is 9.6 GB, Q2_K is 26.4 GB, Q8_0 is 26.7 GB, Q3_K_S is 30.9 GB, Q3_K_M is 34.3 GB, Q3_K_L is 37.1 GB and 6 more.

What context length does AkaLlama llama3 70b v0.1 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 AkaLlama llama3 70b v0.1 GGUF?

The files are on Hugging Face in the snupilab/AkaLlama-llama3-70b-v0.1-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 AkaLlama llama3 70b v0.1 use?

Hugging Face lists the license as other. 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 Llama models

All Llama →

Other large models

All large models →