LL

tsukasa llama 3 70b qlora

LlamaGGUF by ludisUpdated 2024-04-23
Download on Hugging Face
Parameters70.6B
Context8K
Layers80
Architecturellama
Smallest quant26.4 GB
Quick answer

tsukasa llama 3 70b qlora needs about 45.7 GB of memory at Q4_K_M (a 42.5 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 10 quants, from 26.4 GB (Q2_K) to 75.0 GB (Q8_0).

tsukasa llama 3 70b qlora is a 70.6B-parameter Llama model in GGUF format, quantized by ludis. Its trained context length is 8K tokens. The repository has 10 quant files, from 26.4 GB (Q2_K) to 75.0 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K26.4 GB 29.6 GB
Too big Get file →
Q3_K_S30.9 GB 34.1 GB
Too big Get file →
Q3_K_M34.3 GB 37.5 GB
Too big Get file →
Q3_K_L37.1 GB 40.3 GB
Too big Get file →
Q4_K_S40.3 GB 43.5 GB
Too big Get file →
Q4_K_M42.5 GB 45.7 GB
Too big Get file →
Q5_K_S48.7 GB 51.8 GB
Too big Get file →
Q5_K_M49.9 GB 53.1 GB
Too big Get file →
Q6_K57.9 GB (3 parts) 61.1 GB
Too big Get file →
Q8_075.0 GB (3 parts) 78.2 GB
Too big Get file →

What GPU do you need for tsukasa llama 3 70b 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: the best quant that fits is Q2_K (26.4 GB file, about 29.6 GB in use).
  • 48 GB VRAM: the best quant that fits is Q4_K_M (42.5 GB file, about 45.7 GB in use).

Which tsukasa llama 3 70b qlora quant should you choose?

Q4_K_M is the usual starting point for tsukasa llama 3 70b qlora: it balances file size and quality well. Here it is a 42.5 GB file.

The Q8_0 file is 75.0 GB, about 1.8 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is Q2_K at 26.4 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
Parameters70.6B
Layers80
Trained context8,192 tokens
KV cache (fp16)320 KB per token

Source

Quantized byludis
FamilyLlama
Downloads (HF)132
Last updated2024-04-23

Frequently asked questions about tsukasa llama 3 70b qlora

How much VRAM does tsukasa llama 3 70b qlora need?

About 45.7 GB at Q4_K_M with an 8K context window. That is the 42.5 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 tsukasa llama 3 70b qlora on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 29.6 GB, so you would need a larger GPU or CPU offloading.

What is the file size of tsukasa llama 3 70b qlora GGUF?

It depends on the quant: Q2_K is 26.4 GB, Q3_K_S is 30.9 GB, Q3_K_M is 34.3 GB, Q3_K_L is 37.1 GB, Q4_K_S is 40.3 GB, Q4_K_M is 42.5 GB and 4 more.

What context length does tsukasa llama 3 70b qlora support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 2.7 GB at 8K and 2.7 GB at 8K.

Where can I download tsukasa llama 3 70b qlora GGUF?

The files are on Hugging Face in the ludis/tsukasa-llama-3-70b-qlora-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 ludis

All by ludis →

More Llama models

All Llama →

Other large models

All large models →