ME

Magnum Smaug 34b Q8 0

MergekitGGUF by SzilviaBUpdated 2024-10-25
Download on Hugging Face
Parameters34.4B
Context32K
Layers60
Architecturellama
Smallest quant36.5 GB
Quick answer

Magnum Smaug 34b Q8 0 needs about 39.1 GB of memory at Q8_0 (a 36.5 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 8.1 GB.

Magnum Smaug 34b Q8 0 is a 34.4B-parameter Mergekit model in GGUF format, quantized by SzilviaB. Its trained context length is 32K tokens. The repository has 1 quant file, from 36.5 GB (Q8_0) to 36.5 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q8_036.5 GB 39.1 GB
Too big Get file →

What GPU do you need for Magnum Smaug 34b 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: 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 Q8_0 (36.5 GB file, about 39.1 GB in use).

Which Magnum Smaug 34b Q8 0 quant should you choose?

Q8_0 (36.5 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
Parameters34.4B
Layers60
Trained context32,768 tokens
KV cache (fp16)240 KB per token

Source

Quantized bySzilviaB
FamilyMergekit
Downloads (HF)14
Last updated2024-10-25

Frequently asked questions about Magnum Smaug 34b Q8 0

How much VRAM does Magnum Smaug 34b Q8 0 need?

About 39.1 GB at Q8_0 with an 8K context window. That is the 36.5 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 Magnum Smaug 34b Q8 0 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 39.1 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Magnum Smaug 34b Q8 0 GGUF?

It depends on the quant: Q8_0 is 36.5 GB.

What context length does Magnum Smaug 34b Q8 0 support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 2.0 GB at 8K and 8.1 GB at 32K.

Where can I download Magnum Smaug 34b Q8 0 GGUF?

The files are on Hugging Face in the SzilviaB/Magnum_Smaug_34b-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 mergekit-slerp-xirdwrw

Similar models

Browse all →

More from SzilviaB

All by SzilviaB →

More Mergekit models

All Mergekit →

Other large models

All large models →