miquliz 120b needs about 51.0 GB of memory at IQ3_XXS (a 45.9 GB file) with an 8K context window, which is more than a 48 GB GPU holds. Longer context needs more: at 32K tokens the KV cache alone adds about 18.4 GB.
miquliz 120b is a 118B-parameter Miqu model in GGUF format, quantized by wolfram. Its trained context length is 32K tokens. The repository has 1 quant file, from 45.9 GB (IQ3_XXS) to 45.9 GB (IQ3_XXS).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ3_XXS | 45.9 GB | 51.0 GB | Too big | Get file → |
What GPU do you need for miquliz 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 miquliz 120b quant should you choose?
IQ3_XXS (45.9 GB) is the middle option in this repository. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about miquliz 120b
How much VRAM does miquliz 120b need?
About 51.0 GB at IQ3_XXS with an 8K context window. That is the 45.9 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 miquliz 120b on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 51.0 GB, so you would need a larger GPU or CPU offloading.
What is the file size of miquliz 120b GGUF?
It depends on the quant: IQ3_XXS is 45.9 GB.
What context length does miquliz 120b support?
The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 4.6 GB at 8K and 18.4 GB at 32K.
Where can I download miquliz 120b GGUF?
The files are on Hugging Face in the wolfram/miquliz-120b-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.