colossus_120b needs about 41.5 GB of memory at IQ2_S (a 36.4 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 9 quants, from 24.7 GB (IQ1_S) to 48.1 GB (IQ3_XS).
colossus_120b is a 118B-parameter Colossus model in GGUF format, quantized by mradermacher. Its trained context length is 4K tokens. The repository has 9 quant files, from 24.7 GB (IQ1_S) to 48.1 GB (IQ3_XS).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 24.7 GB | 27.5 GB | Too big | Get file → | |
| IQ1_M | 27.1 GB | 29.9 GB | Too big | Get file → | |
| IQ2_XXS | 31.1 GB | 33.9 GB | Too big | Get file → | |
| IQ2_XS | 34.6 GB | 37.4 GB | Too big | Get file → | |
| IQ2_S | 36.4 GB | 39.2 GB | Too big | Get file → | |
| IQ2_M | 39.6 GB | 42.4 GB | Too big | Get file → | |
| Q2_K | 43.2 GB | 46.0 GB | Too big | Get file → | |
| IQ3_XXS | 45.2 GB | 48.0 GB | Too big | Get file → | |
| IQ3_XS | 48.1 GB | 50.9 GB | Too big | Get file → |
What GPU do you need for colossus_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: the best quant that fits is IQ1_S (24.7 GB file, about 29.8 GB in use).
- 48 GB VRAM: the best quant that fits is IQ2_M (39.6 GB file, about 44.7 GB in use).
Which colossus_120b quant should you choose?
IQ2_S (36.4 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.
If memory is tight, the smallest file is IQ1_S at 24.7 GB, with the quality trade-offs that come with fewer bits. 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
Source
Frequently asked questions about colossus_120b
How much VRAM does colossus_120b need?
About 41.5 GB at IQ2_S with an 8K context window. That is the 36.4 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 colossus_120b on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 29.8 GB, so you would need a larger GPU or CPU offloading.
What is the file size of colossus_120b GGUF?
It depends on the quant: IQ1_S is 24.7 GB, IQ1_M is 27.1 GB, IQ2_XXS is 31.1 GB, IQ2_XS is 34.6 GB, IQ2_S is 36.4 GB, IQ2_M is 39.6 GB and 3 more.
What context length does colossus_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 colossus_120b GGUF?
The files are on Hugging Face in the mradermacher/colossus_120b-i1-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 colossus_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.