HE

L3.1 HermesBreakGradientXL 12B Q8 0

HermesbreakgradientxlGGUF by dasChronos1Updated 2024-09-07
Download on Hugging Face
Parameters12.2B
Context128K
Layers51
Architecturellama
Smallest quant12.9 GB
Quick answer

L3.1 HermesBreakGradientXL 12B Q8 0 needs about 15.2 GB of memory at Q8_0 (a 12.9 GB file) with an 8K context window, so it fits on a 16 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 6.8 GB.

L3.1 HermesBreakGradientXL 12B Q8 0 is a 12.2B-parameter Hermesbreakgradientxl model in GGUF format, quantized by dasChronos1. Its trained context length is 128K tokens. The repository has 1 quant file, from 12.9 GB (Q8_0) to 12.9 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q8_012.9 GB 15.2 GB
Too big Get file →

What GPU do you need for L3.1 HermesBreakGradientXL 12B 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: the best quant that fits is Q8_0 (12.9 GB file, about 15.2 GB in use).

Which L3.1 HermesBreakGradientXL 12B Q8 0 quant should you choose?

Q8_0 (12.9 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
Parameters12.2B
Layers51
Trained context131,072 tokens
KV cache (fp16)204 KB per token

Source

Quantized bydasChronos1
Downloads (HF)6
Last updated2024-09-07

Frequently asked questions about L3.1 HermesBreakGradientXL 12B Q8 0

How much VRAM does L3.1 HermesBreakGradientXL 12B Q8 0 need?

About 15.2 GB at Q8_0 with an 8K context window. That is the 12.9 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 L3.1 HermesBreakGradientXL 12B Q8 0 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 15.2 GB, so you would need a larger GPU or CPU offloading.

What is the file size of L3.1 HermesBreakGradientXL 12B Q8 0 GGUF?

It depends on the quant: Q8_0 is 12.9 GB.

What context length does L3.1 HermesBreakGradientXL 12B Q8 0 support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.7 GB at 8K and 6.8 GB at 32K.

Where can I download L3.1 HermesBreakGradientXL 12B Q8 0 GGUF?

The files are on Hugging Face in the dasChronos1/L3.1-HermesBreakGradientXL-12B-Q8_0-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 dasChronos1

All by dasChronos1 →

More Hermesbreakgradientxl models

All Hermesbreakgradientxl →

Other medium models

All medium models →