miqu 1 120b iMat needs about 40.6 GB of memory at IQ2_XS (a 35.4 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 3 quants, from 31.8 GB (IQ2_XXS) to 46.9 GB (IQ3_XXS).
miqu 1 120b iMat is a 120B-parameter Miqu model in GGUF format, quantized by dranger003. Its trained context length is 32K tokens. The repository has 3 quant files, from 31.8 GB (IQ2_XXS) to 46.9 GB (IQ3_XXS).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ2_XXS | 31.8 GB | 37.0 GB | Too big | Get file → | |
| IQ2_XS | 35.4 GB | 40.6 GB | Too big | Get file → | |
| IQ3_XXS | 46.9 GB | 52.1 GB | Too big | Get file → |
What GPU do you need for miqu 1 120b iMat?
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 IQ2_XS (35.4 GB file, about 40.6 GB in use).
Which miqu 1 120b iMat quant should you choose?
IQ2_XS (35.4 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 IQ2_XXS at 31.8 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 miqu 1 120b iMat
How much VRAM does miqu 1 120b iMat need?
About 40.6 GB at IQ2_XS with an 8K context window. That is the 35.4 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 miqu 1 120b iMat on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 37.0 GB, so you would need a larger GPU or CPU offloading.
What is the file size of miqu 1 120b iMat GGUF?
It depends on the quant: IQ2_XXS is 31.8 GB, IQ2_XS is 35.4 GB, IQ3_XXS is 46.9 GB.
What context length does miqu 1 120b iMat support?
The GGUF header lists a trained context length of 32,764 tokens (32K). The KV cache grows with the context you use: about 4.7 GB at 8K and 18.8 GB at 32K.
Where can I download miqu 1 120b iMat GGUF?
The files are on Hugging Face in the dranger003/miqu-1-120b-iMat.GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.