LFM2 24B A2B ROCmFPX needs about 25.2 GB of memory at Q6_0 (a 22.0 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 4 quants, from 13.5 GB (Q4_0) to 25.0 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 10.7 GB.
LFM2 24B A2B ROCmFPX is a 23.8B-parameter Lfm model in GGUF format, quantized by kingjones777. Its trained context length is 125K tokens. The repository has 4 quant files, from 13.5 GB (Q4_0) to 25.0 GB (Q8_0).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_0 | 13.5 GB | 16.7 GB | Too big | Get file → | |
| Q6_0 | 22.0 GB | 25.2 GB | Too big | Get file → | |
| Q8_0 | 24.6 GB | 27.8 GB | Too big | Get file → | |
| Q8_0 | 25.0 GB | 28.2 GB | Too big | Get file → |
What GPU do you need for LFM2 24B A2B ROCmFPX?
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 Q4_0 (13.5 GB file, about 16.7 GB in use).
- 32 GB VRAM: the best quant that fits is Q8_0 (25.0 GB file, about 28.2 GB in use).
Which LFM2 24B A2B ROCmFPX quant should you choose?
Q6_0 (22.0 GB) is the middle option in this repository. Very close to the original quality for most uses, at a clearly larger size than 4-bit.
If memory is tight, the smallest file is Q4_0 at 13.5 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about LFM2 24B A2B ROCmFPX
How much VRAM does LFM2 24B A2B ROCmFPX need?
About 25.2 GB at Q6_0 with an 8K context window. That is the 22.0 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 ROCmFPX on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 16.7 GB, so you would need a larger GPU or CPU offloading.
What is the file size of LFM2 24B A2B ROCmFPX GGUF?
It depends on the quant: Q4_0 is 13.5 GB, Q6_0 is 22.0 GB, Q8_0 is 24.6 GB, Q8_0 is 25.0 GB.
What context length does LFM2 24B A2B ROCmFPX 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 ROCmFPX GGUF?
The files are on Hugging Face in the kingjones777/LFM2-24B-A2B-ROCmFPX-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does LFM2 24B A2B ROCmFPX use?
Hugging Face lists the license as other. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.