EU

Eumyella 120b

EumyellaGGUF by mradermacherUpdated 2024-05-06
Download on Hugging Face
Parameters120B
Context4K
Layers140
Architecturellama
Smallest quant44.5 GB
Quick answer

Eumyella 120b needs about 49.7 GB of memory at Q2_K (a 44.5 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 2 quants, from 44.5 GB (Q2_K) to 49.3 GB (IQ3_XS).

Eumyella 120b is a 120B-parameter Eumyella model in GGUF format, quantized by mradermacher. Its trained context length is 4K tokens. The repository has 2 quant files, from 44.5 GB (Q2_K) to 49.3 GB (IQ3_XS).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K44.5 GB 47.3 GB
Too big Get file →
IQ3_XS49.3 GB 52.2 GB
Too big Get file →

What GPU do you need for Eumyella 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 Eumyella 120b quant should you choose?

Q2_K (44.5 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 bymradermacher
FamilyEumyella
Downloads (HF)25
Last updated2024-05-06

Frequently asked questions about Eumyella 120b

How much VRAM does Eumyella 120b need?

About 49.7 GB at Q2_K with an 8K context window. That is the 44.5 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 Eumyella 120b on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 49.7 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Eumyella 120b GGUF?

It depends on the quant: Q2_K is 44.5 GB, IQ3_XS is 49.3 GB.

What context length does Eumyella 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 Eumyella 120b GGUF?

The files are on Hugging Face in the mradermacher/Eumyella-120b-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Other GGUFs of Eumyella-120b

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Eumyella models

All Eumyella →

Other large models

All large models →