DI

discolm kunoichi 7b german v0.1

DiscolmGGUF by BlizadoUpdated 2024-03-18
Download on Hugging Face
Parameters7.24B
Context8K
Layers32
Architecturellama
Smallest quant4.4 GB
Quick answer

discolm kunoichi 7b german v0.1 needs about 5.9 GB of memory at Q4_K_M (a 4.4 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 3 quants, from 4.4 GB (Q4_K_M) to 7.7 GB.

discolm kunoichi 7b german v0.1 is a 7.24B-parameter Discolm model in GGUF format, quantized by Blizado. Its trained context length is 8K tokens. The repository has 3 quant files, from 4.4 GB (Q4_K_M) to 7.7 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M4.4 GB 5.9 GB
Fits Get file →
Q5_K_M5.1 GB 6.7 GB
Fits Get file →
—7.7 GB 9.3 GB
Too big Get file →

What GPU do you need for discolm kunoichi 7b german v0.1?

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: the best quant that fits is Q4_K_M (4.4 GB file, about 5.9 GB in use).
  • 8 GB VRAM: the best quant that fits is Q5_K_M (5.1 GB file, about 6.7 GB in use).
  • 12 GB VRAM: the best quant that fits is the main file (7.7 GB file, about 9.3 GB in use).

Which discolm kunoichi 7b german v0.1 quant should you choose?

Q4_K_M is the usual starting point for discolm kunoichi 7b german v0.1: it balances file size and quality well. Here it is a 4.4 GB file.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters7.24B
Layers32
Trained context8,192 tokens
KV cache (fp16)128 KB per token

Source

Quantized byBlizado
FamilyDiscolm
Downloads (HF)162
Last updated2024-03-18

Frequently asked questions about discolm kunoichi 7b german v0.1

How much VRAM does discolm kunoichi 7b german v0.1 need?

About 5.9 GB at Q4_K_M with an 8K context window. That is the 4.4 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 discolm kunoichi 7b german v0.1 on an 8 GB GPU?

Yes, with Q5_K_M: the 5.1 GB file needs about 6.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of discolm kunoichi 7b german v0.1 GGUF?

It depends on the quant: Q4_K_M is 4.4 GB, Q5_K_M is 5.1 GB, file is 7.7 GB.

What context length does discolm kunoichi 7b german v0.1 support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 1.1 GB at 8K and 1.1 GB at 8K.

Where can I download discolm kunoichi 7b german v0.1 GGUF?

The files are on Hugging Face in the Blizado/discolm-kunoichi-7b-german-v0.1-gguf repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Similar models

Browse all →

More from Blizado

All by Blizado →

More Discolm models

All Discolm →

Other small models

All small models →