LFM2 24B A2B MXFP4 MOE needs about 17.2 GB of memory at MXFP4_MOE (a 14.0 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 3 quants, from 13.3 GB (MXFP4_MOE) to 14.0 GB (MXFP4_MOE). Longer context needs more: at 32K tokens the KV cache alone adds about 10.7 GB.
LFM2 24B A2B MXFP4 MOE is a 23.8B-parameter Lfm model in GGUF format, quantized by noctrex. Its trained context length is 125K tokens. The repository has 3 quant files, from 13.3 GB (MXFP4_MOE) to 14.0 GB (MXFP4_MOE).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| MXFP4_MOE | 13.3 GB | 16.5 GB | Too big | Get file → | |
| MXFP4_MOE | 14.0 GB | 17.2 GB | Too big | Get file → | |
| MXFP4_MOE | 14.0 GB | 17.2 GB | Too big | Get file → |
What GPU do you need for LFM2 24B A2B 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: the best quant that fits is MXFP4_MOE (14.0 GB file, about 17.2 GB in use).
Which LFM2 24B A2B MXFP4 MOE quant should you choose?
MXFP4_MOE (14.0 GB) is the middle option in this repository. Lower bit counts mean smaller files and more quality loss.
If memory is tight, the smallest file is MXFP4_MOE at 13.3 GB, with the quality trade-offs that come with fewer bits. 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 LFM2 24B A2B MXFP4 MOE
How much VRAM does LFM2 24B A2B MXFP4 MOE need?
About 17.2 GB at MXFP4_MOE with an 8K context window. That is the 14.0 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 LFM2 24B A2B MXFP4 MOE on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 16.5 GB, so you would need a larger GPU or CPU offloading.
What is the file size of LFM2 24B A2B MXFP4 MOE GGUF?
It depends on the quant: MXFP4_MOE is 13.3 GB, MXFP4_MOE is 14.0 GB, MXFP4_MOE is 14.0 GB.
What context length does LFM2 24B A2B MXFP4 MOE support?
The GGUF header lists a trained context length of 128,000 tokens (125K). The KV cache grows with the context you use: about 2.7 GB at 8K and 10.7 GB at 32K.
Where can I download LFM2 24B A2B MXFP4 MOE GGUF?
The files are on Hugging Face in the noctrex/LFM2-24B-A2B-MXFP4_MOE-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.