CO

collosus 120b

ColossusGGUF by mradermacherUpdated 2024-12-16
Download on Hugging Face
Parameters118B
Context4K
Layers137
Architecturellama
Smallest quant43.2 GB
Quick answer

collosus 120b needs about 48.3 GB of memory at Q2_K (a 43.2 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 2 quants, from 43.2 GB (Q2_K) to 48.1 GB (IQ3_XS).

collosus 120b is a 118B-parameter Colossus model in GGUF format, quantized by mradermacher. Its trained context length is 4K tokens. The repository has 2 quant files, from 43.2 GB (Q2_K) to 48.1 GB (IQ3_XS).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K43.2 GB 46.0 GB
Too big Get file →
IQ3_XS48.1 GB 50.9 GB
Too big Get file →

What GPU do you need for collosus 120b?

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 collosus 120b quant should you choose?

Q2_K (43.2 GB) is the middle option in this repository. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters118B
Layers137
Trained context4,096 tokens
KV cache (fp16)548 KB per token

Source

Quantized bymradermacher
FamilyColossus
Licenseapache-2.0
Downloads (HF)39
Last updated2024-12-16

Frequently asked questions about collosus 120b

How much VRAM does collosus 120b need?

About 48.3 GB at Q2_K with an 8K context window. That is the 43.2 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 collosus 120b on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 48.3 GB, so you would need a larger GPU or CPU offloading.

What is the file size of collosus 120b GGUF?

It depends on the quant: Q2_K is 43.2 GB, IQ3_XS is 48.1 GB.

What context length does collosus 120b support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 4.6 GB at 8K and 2.3 GB at 4K.

Where can I download collosus 120b GGUF?

The files are on Hugging Face in the mradermacher/collosus_120b-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 collosus 120b use?

Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Other GGUFs of colossus_120b

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Colossus models

All Colossus →

Other large models

All large models →