CO

cognitivecomputations DolphinHermes 120b

CognitivecomputationsGGUF by RichardErkhovUpdated 2024-07-22
Download on Hugging Face
Parameters120B
Context4K
Layers140
Architecturellama
Smallest quant44.2 GB
Quick answer

cognitivecomputations DolphinHermes 120b needs about 49.4 GB of memory at Q2_K (a 44.2 GB file) with an 8K context window, which is more than a 48 GB GPU holds.

cognitivecomputations DolphinHermes 120b is a 120B-parameter Cognitivecomputations model in GGUF format, quantized by RichardErkhov. Its trained context length is 4K tokens. The repository has 1 quant file, from 44.2 GB (Q2_K) to 44.2 GB (Q2_K).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K44.2 GB (2 parts) 47.0 GB
Too big Get file →

What GPU do you need for cognitivecomputations DolphinHermes 120b?

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 cognitivecomputations DolphinHermes 120b quant should you choose?

Q2_K (44.2 GB) is the middle option in this repository. 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
Parameters120B
Layers140
Trained context4,096 tokens
KV cache (fp16)560 KB per token

Source

Quantized byRichardErkhov
Licensellama2
Downloads (HF)7
Last updated2024-07-22

Frequently asked questions about cognitivecomputations DolphinHermes 120b

How much VRAM does cognitivecomputations DolphinHermes 120b need?

About 49.4 GB at Q2_K with an 8K context window. That is the 44.2 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 cognitivecomputations DolphinHermes 120b on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 49.4 GB, so you would need a larger GPU or CPU offloading.

What is the file size of cognitivecomputations DolphinHermes 120b GGUF?

It depends on the quant: Q2_K is 44.2 GB.

What context length does cognitivecomputations DolphinHermes 120b support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 4.7 GB at 8K and 2.3 GB at 4K.

Where can I download cognitivecomputations DolphinHermes 120b GGUF?

The files are on Hugging Face in the RichardErkhov/cognitivecomputations_-_DolphinHermes-120b-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 cognitivecomputations DolphinHermes 120b use?

Hugging Face lists the license as llama2. 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 RichardErkhov

All by RichardErkhov →

More Cognitivecomputations models

All Cognitivecomputations →

Other large models

All large models →