SorcererLM 8x22b MXFP4 MOE needs about 79.9 GB of memory at MXFP4_MOE (a 77.5 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 7.5 GB.
SorcererLM 8x22b MXFP4 MOE is a 141B-parameter Sorcererlm model in GGUF format, quantized by JeiganS. Its trained context length is 64K tokens. The repository has 1 quant file, from 77.5 GB (MXFP4_MOE) to 77.5 GB (MXFP4_MOE).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| MXFP4_MOE | 77.5 GB | 79.9 GB | Too big | Get file → |
What GPU do you need for SorcererLM 8x22b MXFP4 MOE?
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 SorcererLM 8x22b MXFP4 MOE quant should you choose?
MXFP4_MOE (77.5 GB) is the middle option in this repository. Lower bit counts mean smaller files and more quality loss.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about SorcererLM 8x22b MXFP4 MOE
How much VRAM does SorcererLM 8x22b MXFP4 MOE need?
About 79.9 GB at MXFP4_MOE with an 8K context window. That is the 77.5 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 SorcererLM 8x22b MXFP4 MOE on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 79.9 GB, so you would need a larger GPU or CPU offloading.
What is the file size of SorcererLM 8x22b MXFP4 MOE GGUF?
It depends on the quant: MXFP4_MOE is 77.5 GB.
What context length does SorcererLM 8x22b MXFP4 MOE support?
The GGUF header lists a trained context length of 65,536 tokens (64K). 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 SorcererLM 8x22b MXFP4 MOE GGUF?
The files are on Hugging Face in the JeiganS/SorcererLM-8x22b-MXFP4_MOE repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does SorcererLM 8x22b MXFP4 MOE 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.