PU

pure crush 1.0 zloss instruct

PureGGUF by hushpiperUpdated 2024-02-14
Download on Hugging Face
Parameters45.4B
Context32K
Layers32
Architecturellama
Smallest quant32.2 GB
Quick answer

pure crush 1.0 zloss instruct needs about 33.8 GB of memory at Q5_K_M (a 32.2 GB file) with an 8K context window, so it fits on a 48 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

pure crush 1.0 zloss instruct is a 45.4B-parameter Pure model in GGUF format, quantized by hushpiper. Its trained context length is 32K tokens. The repository has 1 quant file, from 32.2 GB (Q5_K_M) to 32.2 GB (Q5_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q5_K_M32.2 GB 33.8 GB
Too big Get file →

What GPU do you need for pure crush 1.0 zloss instruct?

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: the best quant that fits is Q5_K_M (32.2 GB file, about 33.8 GB in use).

Which pure crush 1.0 zloss instruct quant should you choose?

Q5_K_M (32.2 GB) is the middle option in this repository. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters45.4B (approximate, mixture of experts)
Layers32
Trained context32,768 tokens
KV cache (fp16)128 KB per token

Source

Quantized byhushpiper
FamilyPure
Downloads (HF)11
Last updated2024-02-14

Frequently asked questions about pure crush 1.0 zloss instruct

How much VRAM does pure crush 1.0 zloss instruct need?

About 33.8 GB at Q5_K_M with an 8K context window. That is the 32.2 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 pure crush 1.0 zloss instruct on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 33.8 GB, so you would need a larger GPU or CPU offloading.

What is the file size of pure crush 1.0 zloss instruct GGUF?

It depends on the quant: Q5_K_M is 32.2 GB.

What context length does pure crush 1.0 zloss instruct support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.

Where can I download pure crush 1.0 zloss instruct GGUF?

The files are on Hugging Face in the hushpiper/pure-crush-1.0-zloss-instruct-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 Pure models

All Pure →

Other large models

All large models →