MA

magnum v4 123b

MagnumGGUF by anthracite-orgUpdated 2024-11-25
Download on Hugging Face
Parameters123B
Context128K
Layers88
Architecturellama
Smallest quant64.6 GB
Quick answer

magnum v4 123b needs about 76.7 GB of memory at Q4_K_M (a 73.2 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 5 quants, from 64.6 GB (Q3_K_L) to 130.3 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 11.8 GB.

magnum v4 123b is a 123B-parameter Magnum model in GGUF format, quantized by anthracite-org. Its trained context length is 128K tokens. The repository has 5 quant files, from 64.6 GB (Q3_K_L) to 130.3 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_K_L64.6 GB (3 parts) 68.0 GB
Too big Get file →
Q4_K_M73.2 GB (3 parts) 76.7 GB
Too big Get file →
Q5_K_M86.5 GB (3 parts) 89.9 GB
Too big Get file →
Q6_K100.6 GB (4 parts) 104.0 GB
Too big Get file →
Q8_0130.3 GB (5 parts) 133.7 GB
Too big Get file →

What GPU do you need for magnum v4 123b?

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: no quant fits at an 8K context.

Which magnum v4 123b quant should you choose?

Q4_K_M is the usual starting point for magnum v4 123b: it balances file size and quality well. Here it is a 73.2 GB file.

The Q8_0 file is 130.3 GB, about 1.8 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is Q3_K_L at 64.6 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters123B
Layers88
Trained context131,072 tokens
KV cache (fp16)352 KB per token

Source

Quantized byanthracite-org
FamilyMagnum
Licenseother
Downloads (HF)417
Last updated2024-11-25

Frequently asked questions about magnum v4 123b

How much VRAM does magnum v4 123b need?

About 76.7 GB at Q4_K_M with an 8K context window. That is the 73.2 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 magnum v4 123b on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 68.0 GB, so you would need a larger GPU or CPU offloading.

What is the file size of magnum v4 123b GGUF?

It depends on the quant: Q3_K_L is 64.6 GB, Q4_K_M is 73.2 GB, Q5_K_M is 86.5 GB, Q6_K is 100.6 GB, Q8_0 is 130.3 GB.

What context length does magnum v4 123b support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 3.0 GB at 8K and 11.8 GB at 32K.

Where can I download magnum v4 123b GGUF?

The files are on Hugging Face in the anthracite-org/magnum-v4-123b-gguf repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does magnum v4 123b use?

Hugging Face lists the license as other. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Similar models

Browse all →

More from anthracite-org

All by anthracite-org →

More Magnum models

All Magnum →

Other large models

All large models →