BE

Behemoth 123B v2

BehemothGGUF by TheDrummerUpdated 2024-11-24
Download on Hugging Face
Parameters123B
Context128K
Layers88
Architecturellama
Smallest quant45.2 GB
Quick answer

Behemoth 123B v2 needs about 76.7 GB of memory at Q4_K_M (a 73.2 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 7 quants, from 45.2 GB (Q2_K) to 245.2 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 11.8 GB.

Behemoth 123B v2 is a 123B-parameter Behemoth model in GGUF format, quantized by TheDrummer. Its trained context length is 128K tokens. The repository has 7 quant files, from 45.2 GB (Q2_K) to 245.2 GB (BF16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K45.2 GB (2 parts) 48.6 GB
Too big Get file →
Q3_K_M59.1 GB (2 parts) 62.6 GB
Too big Get file →
Q4_K_M73.2 GB (2 parts) 76.7 GB
Too big Get file →
Q5_K_M86.5 GB (2 parts) 89.9 GB
Too big Get file →
Q6_K100.6 GB (3 parts) 104.0 GB
Too big Get file →
Q8_0130.3 GB (3 parts) 133.7 GB
Too big Get file →
BF16245.2 GB (6 parts) 248.7 GB
Too big Get file →

What GPU do you need for Behemoth 123B v2?

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 Behemoth 123B v2 quant should you choose?

Q4_K_M is the usual starting point for Behemoth 123B v2: it balances file size and quality well. Here it is a 73.2 GB file.

The Q8_0 file is 130.3 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 45.2 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
Parameters123B
Layers88
Trained context131,072 tokens
KV cache (fp16)352 KB per token

Source

Quantized byTheDrummer
FamilyBehemoth
Licenseother
Downloads (HF)138
Last updated2024-11-24

Frequently asked questions about Behemoth 123B v2

How much VRAM does Behemoth 123B v2 need?

About 76.7 GB at Q4_K_M with an 8K context window. That is the 73.2 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 Behemoth 123B v2 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 48.6 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Behemoth 123B v2 GGUF?

It depends on the quant: Q2_K is 45.2 GB, Q3_K_M is 59.1 GB, Q4_K_M is 73.2 GB, Q5_K_M is 86.5 GB, Q6_K is 100.6 GB, Q8_0 is 130.3 GB and 1 more.

What context length does Behemoth 123B v2 support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 3.0 GB at 8K and 11.8 GB at 32K.

Where can I download Behemoth 123B v2 GGUF?

The files are on Hugging Face in the TheDrummer/Behemoth-123B-v2-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 Behemoth 123B v2 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 from TheDrummer

All by TheDrummer →

More Behemoth models

All Behemoth →

Other large models

All large models →