TI

Tiramisu Q4 K M test

TiramisuGGUF by matchaquantUpdated 2024-09-11
Download on Hugging Face
Parameters12.2B
Context1000K
Layers40
Architecturellama
Smallest quant7.5 GB
Quick answer

Tiramisu Q4 K M test needs about 9.3 GB of memory at its main file (a 7.5 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 3 quants, from 7.5 GB to 13.0 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.

Tiramisu Q4 K M test is a 12.2B-parameter Tiramisu model in GGUF format, quantized by matchaquant. Its trained context length is 1000K tokens. The repository has 3 quant files, from 7.5 GB to 13.0 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—7.5 GB 9.3 GB
Too big Get file →
—7.5 GB 9.3 GB
Too big Get file →
—13.0 GB 14.9 GB
Too big Get file →

What GPU do you need for Tiramisu Q4 K M test?

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: the best quant that fits is the main file (7.5 GB file, about 9.3 GB in use).
  • 16 GB VRAM: the best quant that fits is the main file (13.0 GB file, about 14.9 GB in use).

Which Tiramisu Q4 K M test quant should you choose?

If memory is tight, the smallest file is the first one in the table at 7.5 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters12.2B
Layers40
Trained context1,024,000 tokens
KV cache (fp16)160 KB per token

Source

Quantized bymatchaquant
FamilyTiramisu
Licenseapache-2.0
Downloads (HF)13
Last updated2024-09-11

Frequently asked questions about Tiramisu Q4 K M test

How much VRAM does Tiramisu Q4 K M test need?

About 9.3 GB at its main file with an 8K context window. That is the 7.5 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 Tiramisu Q4 K M test on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 9.3 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Tiramisu Q4 K M test GGUF?

It depends on the quant: file is 7.5 GB, file is 7.5 GB, file is 13.0 GB.

What context length does Tiramisu Q4 K M test support?

The GGUF header lists a trained context length of 1,024,000 tokens (1000K). The KV cache grows with the context you use: about 1.3 GB at 8K and 5.4 GB at 32K.

Where can I download Tiramisu Q4 K M test GGUF?

The files are on Hugging Face in the matchaquant/Tiramisu-Q4_K_M-test repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Tiramisu Q4 K M test use?

Hugging Face lists the license as apache-2.0. 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 Tiramisu models

All Tiramisu →

Other medium models

All medium models →