ultiima 108B i1 needs about 45.7 GB of memory at IQ2_S (a 41.2 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 10 quants, from 33.4 GB (IQ1_S) to 48.4 GB (IQ3_XS). Longer context needs more: at 32K tokens the KV cache alone adds about 16.1 GB.
ultiima 108B i1 is a 108B-parameter Ultiima model in GGUF format, quantized by mradermacher. Its trained context length is 128K tokens. The repository has 10 quant files, from 33.4 GB (IQ1_S) to 48.4 GB (IQ3_XS).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 33.4 GB | 37.9 GB | Too big | Get file → | |
| IQ1_M | 35.0 GB | 39.5 GB | Too big | Get file → | |
| IQ2_XXS | 37.6 GB | 42.1 GB | Too big | Get file → | |
| IQ2_XS | 40.0 GB | 44.5 GB | Too big | Get file → | |
| IQ2_S | 41.2 GB | 45.7 GB | Too big | Get file → | |
| IQ2_M | 43.3 GB | 47.8 GB | Too big | Get file → | |
| Q2_K_S | 43.5 GB | 48.0 GB | Too big | Get file → | |
| Q2_K | 43.9 GB | 48.4 GB | Too big | Get file → | |
| IQ3_XXS | 46.9 GB | 51.5 GB | Too big | Get file → | |
| IQ3_XS | 48.4 GB | 52.9 GB | Too big | Get file → |
What GPU do you need for ultiima 108B i1?
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 Q2_K_S (43.5 GB file, about 48.0 GB in use).
Which ultiima 108B i1 quant should you choose?
IQ2_S (41.2 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.
If memory is tight, the smallest file is IQ1_S at 33.4 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 ultiima 108B i1
How much VRAM does ultiima 108B i1 need?
About 45.7 GB at IQ2_S with an 8K context window. That is the 41.2 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 ultiima 108B i1 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 37.9 GB, so you would need a larger GPU or CPU offloading.
What is the file size of ultiima 108B i1 GGUF?
It depends on the quant: IQ1_S is 33.4 GB, IQ1_M is 35.0 GB, IQ2_XXS is 37.6 GB, IQ2_XS is 40.0 GB, IQ2_S is 41.2 GB, IQ2_M is 43.3 GB and 4 more.
What context length does ultiima 108B i1 support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 4.0 GB at 8K and 16.1 GB at 32K.
Where can I download ultiima 108B i1 GGUF?
The files are on Hugging Face in the mradermacher/ultiima-108B-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 ultiima 108B i1 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.