Blitz AI ULTRA i1 needs about 77.9 GB of memory at IQ2_XXS (a 38.7 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 6 quants, from 32.3 GB (IQ1_S) to 48.3 GB (IQ2_M). Longer context needs more: at 32K tokens the KV cache alone adds about 154.6 GB.
Blitz AI ULTRA i1 is a 128B-parameter Blitz model in GGUF format, quantized by mradermacher. Its trained context length is 32K tokens. The repository has 6 quant files, from 32.3 GB (IQ1_S) to 48.3 GB (IQ2_M).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 32.3 GB | 71.5 GB | Too big | Get file → | |
| IQ1_M | 34.7 GB | 73.9 GB | Too big | Get file → | |
| IQ2_XXS | 38.7 GB | 77.9 GB | Too big | Get file → | |
| IQ2_XS | 42.2 GB | 81.4 GB | Too big | Get file → | |
| IQ2_S | 45.1 GB | 84.2 GB | Too big | Get file → | |
| IQ2_M | 48.3 GB | 87.4 GB | Too big | Get file → |
What GPU do you need for Blitz AI ULTRA 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: no quant fits at an 8K context.
Which Blitz AI ULTRA i1 quant should you choose?
IQ2_XXS (38.7 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 32.3 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 Blitz AI ULTRA i1
How much VRAM does Blitz AI ULTRA i1 need?
About 77.9 GB at IQ2_XXS with an 8K context window. That is the 38.7 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 Blitz AI ULTRA i1 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 71.5 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Blitz AI ULTRA i1 GGUF?
It depends on the quant: IQ1_S is 32.3 GB, IQ1_M is 34.7 GB, IQ2_XXS is 38.7 GB, IQ2_XS is 42.2 GB, IQ2_S is 45.1 GB, IQ2_M is 48.3 GB.
What context length does Blitz AI ULTRA i1 support?
The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 38.7 GB at 8K and 154.6 GB at 32K.
Where can I download Blitz AI ULTRA i1 GGUF?
The files are on Hugging Face in the mradermacher/Blitz-AI-ULTRA-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 Blitz AI ULTRA i1 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.