LL

Tess 3 Llama 3.1 405B

LlamaGGUF by bartowskiUpdated 2024-09-03
Download on Hugging Face
Parameters410B
Context128K
Layers126
Architecturellama
Smallest quant95.1 GB
Quick answer

Tess 3 Llama 3.1 405B needs about 254.7 GB of memory at Q4_K_M (a 245.7 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 20 quants, from 95.1 GB (IQ1_M) to 435.7 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 33.8 GB.

Tess 3 Llama 3.1 405B is a 410B-parameter Llama model in GGUF format, quantized by bartowski. Its trained context length is 128K tokens. The repository has 20 quant files, from 95.1 GB (IQ1_M) to 435.7 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_M95.1 GB (3 parts) 104.1 GB
Too big Get file →
IQ2_XXS109.0 GB (3 parts) 118.0 GB
Too big Get file →
IQ2_XS121.1 GB (4 parts) 130.1 GB
Too big Get file →
IQ2_M138.5 GB (4 parts) 147.5 GB
Too big Get file →
Q2_K151.2 GB (4 parts) 160.2 GB
Too big Get file →
Q2_K_L153.3 GB (4 parts) 162.2 GB
Too big Get file →
IQ3_XXS157.7 GB (4 parts) 166.7 GB
Too big Get file →
Q3_K_S177.1 GB (5 parts) 186.0 GB
Too big Get file →
IQ3_M183.8 GB (5 parts) 192.8 GB
Too big Get file →
Q3_K_M197.5 GB (5 parts) 206.4 GB
Too big Get file →
Q3_K_L215.2 GB (6 parts) 224.2 GB
Too big Get file →
Q3_K_XL217.0 GB (6 parts) 226.0 GB
Too big Get file →
IQ4_XS219.1 GB (6 parts) 228.1 GB
Too big Get file →
Q4_0231.2 GB (6 parts) 240.2 GB
Too big Get file →
Q4_0232.1 GB (6 parts) 241.0 GB
Too big Get file →
Q4_K_S232.9 GB (6 parts) 241.8 GB
Too big Get file →
Q4_K_M245.7 GB (7 parts) 254.7 GB
Too big Get file →
Q5_K_M289.7 GB (8 parts) 298.6 GB
Too big Get file →
Q6_K336.4 GB (9 parts) 345.4 GB
Too big Get file →
Q8_0435.7 GB (12 parts) 444.7 GB
Too big Get file →

What GPU do you need for Tess 3 Llama 3.1 405B?

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: no quant fits at an 8K context.
  • 48 GB VRAM: no quant fits at an 8K context.

Which Tess 3 Llama 3.1 405B quant should you choose?

Q4_K_M is the usual starting point for Tess 3 Llama 3.1 405B: it balances file size and quality well. Here it is a 245.7 GB file.

The Q8_0 file is 435.7 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 IQ1_M at 95.1 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
Parameters410B
Layers126
Trained context131,072 tokens
KV cache (fp16)1008 KB per token

Source

Quantized bybartowski
FamilyLlama
Licensellama3.1
Downloads (HF)474
Last updated2024-09-03

Frequently asked questions about Tess 3 Llama 3.1 405B

How much VRAM does Tess 3 Llama 3.1 405B need?

About 254.7 GB at Q4_K_M with an 8K context window. That is the 245.7 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 Tess 3 Llama 3.1 405B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 104.1 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Tess 3 Llama 3.1 405B GGUF?

It depends on the quant: IQ1_M is 95.1 GB, IQ2_XXS is 109.0 GB, IQ2_XS is 121.1 GB, IQ2_M is 138.5 GB, Q2_K is 151.2 GB, Q2_K_L is 153.3 GB and 14 more.

What context length does Tess 3 Llama 3.1 405B support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 8.5 GB at 8K and 33.8 GB at 32K.

Where can I download Tess 3 Llama 3.1 405B GGUF?

The files are on Hugging Face in the bartowski/Tess-3-Llama-3.1-405B-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 Tess 3 Llama 3.1 405B use?

Hugging Face lists the license as llama3.1. 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 bartowski

All by bartowski →

More Llama models

All Llama →

Other large models

All large models →