KU

KuroMitsu 11B

KuromitsuGGUF by Artefact2Updated 2024-01-27
Download on Hugging Face
Parameters10.7B
Context8K
Layers48
Architecturellama
Smallest quant2.9 GB
Quick answer

KuroMitsu 11B needs about 8.6 GB of memory at Q4_K_M (a 6.5 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 13 quants, from 2.9 GB (IQ2_XXS) to 8.8 GB (Q6_K).

KuroMitsu 11B is a 10.7B-parameter Kuromitsu model in GGUF format, quantized by Artefact2. Its trained context length is 8K tokens. The repository has 13 quant files, from 2.9 GB (IQ2_XXS) to 8.8 GB (Q6_K).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ2_XXS2.9 GB 5.0 GB
Fits Get file →
IQ2_XS3.2 GB 5.3 GB
Fits Get file →
Q2_K_S3.7 GB 5.8 GB
Fits Get file →
Q2_K4.0 GB 6.1 GB
Fits Get file →
Q3_K_XS4.4 GB 6.5 GB
Fits Get file →
Q3_K_S4.7 GB 6.8 GB
Fits Get file →
Q3_K_M5.2 GB 7.3 GB
Tight Get file →
Q3_K_L5.7 GB 7.8 GB
Tight Get file →
Q4_K_S6.1 GB 8.2 GB
Too big Get file →
Q4_K_M6.5 GB 8.6 GB
Too big Get file →
Q5_K_S7.4 GB 9.5 GB
Too big Get file →
Q5_K_M7.6 GB 9.7 GB
Too big Get file →
Q6_K8.8 GB 10.9 GB
Too big Get file →

What GPU do you need for KuroMitsu 11B?

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 Q2_K_S (3.7 GB file, about 5.8 GB in use).
  • 8 GB VRAM: the best quant that fits is Q3_K_L (5.7 GB file, about 7.8 GB in use).
  • 12 GB VRAM: the best quant that fits is Q6_K (8.8 GB file, about 10.9 GB in use).

Which KuroMitsu 11B quant should you choose?

Q4_K_M is the usual starting point for KuroMitsu 11B: it balances file size and quality well. Here it is a 6.5 GB file.

If memory is tight, the smallest file is IQ2_XXS at 2.9 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
Parameters10.7B
Layers48
Trained context8,192 tokens
KV cache (fp16)192 KB per token

Source

Quantized byArtefact2
FamilyKuromitsu
Downloads (HF)45
Last updated2024-01-27

Frequently asked questions about KuroMitsu 11B

How much VRAM does KuroMitsu 11B need?

About 8.6 GB at Q4_K_M with an 8K context window. That is the 6.5 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 KuroMitsu 11B on an 8 GB GPU?

Yes, with Q3_K_L: the 5.7 GB file needs about 7.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of KuroMitsu 11B GGUF?

It depends on the quant: IQ2_XXS is 2.9 GB, IQ2_XS is 3.2 GB, Q2_K_S is 3.7 GB, Q2_K is 4.0 GB, Q3_K_XS is 4.4 GB, Q3_K_S is 4.7 GB and 7 more.

What context length does KuroMitsu 11B support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 1.6 GB at 8K and 1.6 GB at 8K.

Where can I download KuroMitsu 11B GGUF?

The files are on Hugging Face in the Artefact2/KuroMitsu-11B-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 KuroMitsu 11B use?

Hugging Face lists the license as cc-by-nc-4.0. 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 Artefact2

All by Artefact2 →

More Kuromitsu models

All Kuromitsu →

Other medium models

All medium models →