TO

tora 13b v1.0

ToraGGUF by NikolayKozloffUpdated 2023-10-09
Download on Hugging Face
Parameters13B
Context4K
Layers40
Architecturellama
Smallest quant8.2 GB
Quick answer

tora 13b v1.0 needs about 15.4 GB of memory at Q4_1 (a 8.2 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 2 quants, from 8.2 GB (Q4_1) to 10.7 GB (Q6_K).

tora 13b v1.0 is a 13B-parameter Tora model in GGUF format, quantized by NikolayKozloff. Its trained context length is 4K tokens. The repository has 2 quant files, from 8.2 GB (Q4_1) to 10.7 GB (Q6_K).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_18.2 GB 12.0 GB
Too big Get file →
Q6_K10.7 GB 14.5 GB
Too big Get file →

What GPU do you need for tora 13b v1.0?

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: the best quant that fits is Q4_1 (8.2 GB file, about 15.4 GB in use).
  • 24 GB VRAM: the best quant that fits is Q6_K (10.7 GB file, about 17.9 GB in use).

Which tora 13b v1.0 quant should you choose?

Q4_1 (8.2 GB) is the middle option in this repository. 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
Parameters13B
Layers40
Trained context4,096 tokens
KV cache (fp16)800 KB per token

Source

Quantized byNikolayKozloff
FamilyTora
Downloads (HF)7
Last updated2023-10-09

Frequently asked questions about tora 13b v1.0

How much VRAM does tora 13b v1.0 need?

About 15.4 GB at Q4_1 with an 8K context window. That is the 8.2 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 tora 13b v1.0 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 15.4 GB, so you would need a larger GPU or CPU offloading.

What is the file size of tora 13b v1.0 GGUF?

It depends on the quant: Q4_1 is 8.2 GB, Q6_K is 10.7 GB.

What context length does tora 13b v1.0 support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 6.7 GB at 8K and 3.4 GB at 4K.

Where can I download tora 13b v1.0 GGUF?

The files are on Hugging Face in the NikolayKozloff/tora-13b-v1.0 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 NikolayKozloff

All by NikolayKozloff →

More Tora models

All Tora →

Other medium models

All medium models →