GE

em german 70b v01

GermanGGUF by jphmeUpdated 2023-10-12
Download on Hugging Face
Parameters69B
Context4K
Layers80
Architecturellama
Smallest quant39.1 GB
Quick answer

em german 70b v01 needs about 44.6 GB of memory at Q4_K_M (a 41.4 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 4 quants, from 39.1 GB (Q4_K_S) to 48.8 GB (Q5_K_M).

em german 70b v01 is a 69B-parameter German model in GGUF format, quantized by jphme. Its trained context length is 4K tokens. The repository has 4 quant files, from 39.1 GB (Q4_K_S) to 48.8 GB (Q5_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_S39.1 GB 40.9 GB
Too big Get file →
Q4_K_M41.4 GB 43.3 GB
Too big Get file →
Q5_K_S47.5 GB 49.3 GB
Too big Get file →
Q5_K_M48.8 GB 50.6 GB
Too big Get file →

What GPU do you need for em german 70b v01?

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: the best quant that fits is Q4_K_M (41.4 GB file, about 44.6 GB in use).

Which em german 70b v01 quant should you choose?

Q4_K_M is the usual starting point for em german 70b v01: it balances file size and quality well. Here it is a 41.4 GB file.

If memory is tight, the smallest file is Q4_K_S at 39.1 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters69B
Layers80
Trained context4,096 tokens
KV cache (fp16)320 KB per token

Source

Quantized byjphme
FamilyGerman
Licensellama2
Downloads (HF)148
Last updated2023-10-12

Frequently asked questions about em german 70b v01

How much VRAM does em german 70b v01 need?

About 44.6 GB at Q4_K_M with an 8K context window. That is the 41.4 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 em german 70b v01 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 42.3 GB, so you would need a larger GPU or CPU offloading.

What is the file size of em german 70b v01 GGUF?

It depends on the quant: Q4_K_S is 39.1 GB, Q4_K_M is 41.4 GB, Q5_K_S is 47.5 GB, Q5_K_M is 48.8 GB.

What context length does em german 70b v01 support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 2.7 GB at 8K and 1.3 GB at 4K.

Where can I download em german 70b v01 GGUF?

The files are on Hugging Face in the jphme/em_german_70b_v01_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 em german 70b v01 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 jphme

All by jphme →

More German models

All German →

Other large models

All large models →