TS

tsukasa 120b qlora

TsukasaGGUF by bcseUpdated 2024-01-24
Download on Hugging Face
Parameters118B
Context4K
Layers137
Architecturellama
Smallest quant43.2 GB
Quick answer

tsukasa 120b qlora needs about 48.3 GB of memory at Q2_K (a 43.2 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 2 quants, from 43.2 GB (Q2_K) to 47.9 GB (Q3_K_XS).

tsukasa 120b qlora is a 118B-parameter Tsukasa model in GGUF format, quantized by bcse. Its trained context length is 4K tokens. The repository has 2 quant files, from 43.2 GB (Q2_K) to 47.9 GB (Q3_K_XS).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K43.2 GB 46.0 GB
Too big Get file →
Q3_K_XS47.9 GB 50.7 GB
Too big Get file →

What GPU do you need for tsukasa 120b qlora?

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: no quant fits at an 8K context.

Which tsukasa 120b qlora quant should you choose?

Q2_K (43.2 GB) is the middle option in this repository. 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
Parameters118B
Layers137
Trained context4,096 tokens
KV cache (fp16)548 KB per token

Source

Quantized bybcse
FamilyTsukasa
Licensellama2
Downloads (HF)26
Last updated2024-01-24

Frequently asked questions about tsukasa 120b qlora

How much VRAM does tsukasa 120b qlora need?

About 48.3 GB at Q2_K with an 8K context window. That is the 43.2 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 tsukasa 120b qlora on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 48.3 GB, so you would need a larger GPU or CPU offloading.

What is the file size of tsukasa 120b qlora GGUF?

It depends on the quant: Q2_K is 43.2 GB, Q3_K_XS is 47.9 GB.

What context length does tsukasa 120b qlora support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 4.6 GB at 8K and 2.3 GB at 4K.

Where can I download tsukasa 120b qlora GGUF?

The files are on Hugging Face in the bcse/tsukasa-120b-qlora-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 tsukasa 120b qlora 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 bcse

All by bcse →

More Tsukasa models

All Tsukasa →

Other large models

All large models →