ME

Magnum Smaug 34b Q4 K M

MergekitGGUF by SzilviaBUpdated 2024-09-28
Download on Hugging Face
Parameters34.4B
Context32K
Layers60
Architecturellama
Smallest quant41.3 GB
Quick answer

Magnum Smaug 34b Q4 K M needs about 43.8 GB of memory at Q4_K_M (a 41.3 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 Q4 K M 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 41.3 GB (Q4_K_M) to 41.3 GB (Q4_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M41.3 GB (4 parts) 43.8 GB
Too big Get file →

What GPU do you need for Magnum Smaug 34b Q4 K M?

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 Q4_K_M (41.3 GB file, about 43.8 GB in use).

Which Magnum Smaug 34b Q4 K M quant should you choose?

Q4_K_M is the usual starting point for Magnum Smaug 34b Q4 K M: it balances file size and quality well. Here it is a 41.3 GB file.

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)16
Last updated2024-09-28

Frequently asked questions about Magnum Smaug 34b Q4 K M

How much VRAM does Magnum Smaug 34b Q4 K M need?

About 43.8 GB at Q4_K_M with an 8K context window. That is the 41.3 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 Q4 K M on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 43.8 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Magnum Smaug 34b Q4 K M GGUF?

It depends on the quant: Q4_K_M is 41.3 GB.

What context length does Magnum Smaug 34b Q4 K M 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 Q4 K M GGUF?

The files are on Hugging Face in the SzilviaB/Magnum_Smaug_34b-Q4_K_M-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 →