OP

OpenCrystal 15B L3 v3 Q8 0

OpencrystalGGUF by dasChronos1Updated 2024-09-05
Download on Hugging Face
Parameters15B
Context8K
Layers64
Architecturellama
Smallest quant16.0 GB
Quick answer

OpenCrystal 15B L3 v3 Q8 0 needs about 18.6 GB of memory at Q8_0 (a 16.0 GB file) with an 8K context window, so it fits on a 24 GB GPU.

OpenCrystal 15B L3 v3 Q8 0 is a 15B-parameter Opencrystal model in GGUF format, quantized by dasChronos1. Its trained context length is 8K tokens. The repository has 1 quant file, from 16.0 GB (Q8_0) to 16.0 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q8_016.0 GB 18.6 GB
Too big Get file →

What GPU do you need for OpenCrystal 15B L3 v3 Q8 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: no quant fits at an 8K context.
  • 24 GB VRAM: the best quant that fits is Q8_0 (16.0 GB file, about 18.6 GB in use).

Which OpenCrystal 15B L3 v3 Q8 0 quant should you choose?

Q8_0 (16.0 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters15B
Layers64
Trained context8,192 tokens
KV cache (fp16)256 KB per token

Source

Quantized bydasChronos1
Downloads (HF)7
Last updated2024-09-05

Frequently asked questions about OpenCrystal 15B L3 v3 Q8 0

How much VRAM does OpenCrystal 15B L3 v3 Q8 0 need?

About 18.6 GB at Q8_0 with an 8K context window. That is the 16.0 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 OpenCrystal 15B L3 v3 Q8 0 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 18.6 GB, so you would need a larger GPU or CPU offloading.

What is the file size of OpenCrystal 15B L3 v3 Q8 0 GGUF?

It depends on the quant: Q8_0 is 16.0 GB.

What context length does OpenCrystal 15B L3 v3 Q8 0 support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 2.1 GB at 8K and 2.1 GB at 8K.

Where can I download OpenCrystal 15B L3 v3 Q8 0 GGUF?

The files are on Hugging Face in the dasChronos1/OpenCrystal-15B-L3-v3-Q8_0-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Other GGUFs of OpenCrystal-15B-L3-v3

Similar models

Browse all →

More from dasChronos1

All by dasChronos1 →

More Opencrystal models

All Opencrystal →

Other medium models

All medium models →