mexa-22b needs about 40.3 GB of memory at IQ2_XXS (a 37.9 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 6 quants, from 29.7 GB (IQ1_S) to 46.7 GB (IQ2_M). Longer context needs more: at 32K tokens the KV cache alone adds about 7.5 GB.
mexa-22b is a 141B-parameter Mexa model in GGUF format, quantized by mradermacher. Its trained context length is 32K tokens. The repository has 6 quant files, from 29.7 GB (IQ1_S) to 46.7 GB (IQ2_M).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 29.7 GB | 32.0 GB | Too big | Get file → | |
| IQ1_M | 32.7 GB | 35.1 GB | Too big | Get file → | |
| IQ2_XXS | 37.9 GB | 40.3 GB | Too big | Get file → | |
| IQ2_XS | 42.0 GB | 44.4 GB | Too big | Get file → | |
| IQ2_S | 42.6 GB | 45.0 GB | Too big | Get file → | |
| IQ2_M | 46.7 GB | 49.1 GB | Too big | Get file → |
What GPU do you need for mexa-22b?
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 (29.7 GB file, about 32.0 GB in use).
- 48 GB VRAM: the best quant that fits is IQ2_S (42.6 GB file, about 45.0 GB in use).
Which mexa-22b quant should you choose?
IQ2_XXS (37.9 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 29.7 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 mexa-22b
How much VRAM does mexa-22b need?
About 40.3 GB at IQ2_XXS with an 8K context window. That is the 37.9 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 mexa-22b on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 32.0 GB, so you would need a larger GPU or CPU offloading.
What is the file size of mexa-22b GGUF?
It depends on the quant: IQ1_S is 29.7 GB, IQ1_M is 32.7 GB, IQ2_XXS is 37.9 GB, IQ2_XS is 42.0 GB, IQ2_S is 42.6 GB, IQ2_M is 46.7 GB.
What context length does mexa-22b support?
The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.9 GB at 8K and 7.5 GB at 32K.
Where can I download mexa-22b GGUF?
The files are on Hugging Face in the mradermacher/mexa-22b-i1-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.