LFM2.5 24B A2B needs about 18.1 GB of memory at Q4_K_M (a 15.0 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 4 quants, from 0.1 GB to 17.4 GB (Q5_K_M). Longer context needs more: at 32K tokens the KV cache alone adds about 10.7 GB.
24B-parameter reasoning model with 2B active parameters
LFM2.5 24B A2B is a text‑only reasoning model built for fast, private agents on device. It uses a mixture of experts architecture with 64 experts per block and a 131,072 token context length. The model is efficient, running up to 1.7× faster than comparable MoEs on device.
Good at
- Reasoning before answering
- Tool‑calling in agent harnesses
- Fast inference on Apple M5 Max and NVIDIA B300
Limits
- No vision support
- Requires large VRAM for full precision
- License is other
Best for
- On‑device private agents
- Tool‑calling workflows
- Reasoning‑heavy tasks with retrieval
Who it’s for. Developers building private agents that need to reason and call tools locally. The model is suitable for environments where on‑device inference and privacy are priorities.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.1 GB | 3.3 GB | Fits | Get file → | |
| IQ4_XS | 13.3 GB | 16.5 GB | Too big | Get file → | |
| Q4_K_M | 15.0 GB | 18.1 GB | Too big | Get file → | |
| Q5_K_M | 17.4 GB | 20.6 GB | Too big | Get file → |
For 8 GB VRAM, use IQ4_XS (13.3 GB file, 16.5 GB memory at 8K context). For 16 GB VRAM, Q4_K_M (14.95 GB file, 18.1 GB memory) is a balanced choice. If you have 20 GB or more, Q5_K_M (17.37 GB file, 20.6 GB memory) gives the best BF16‑like quality.
What GPU do you need for LFM2.5 24B A2B?
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: the best quant that fits is the main file (0.1 GB file, about 3.3 GB in use).
- 6 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 3.3 GB in use).
- 8 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 3.3 GB in use).
- 12 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 3.3 GB in use).
- 16 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 3.3 GB in use).
- 24 GB VRAM: the best quant that fits is Q5_K_M (17.4 GB file, about 20.6 GB in use).
Which LFM2.5 24B A2B quant should you choose?
Q4_K_M is the usual starting point for LFM2.5 24B A2B: it balances file size and quality well. Here it is a 15.0 GB file.
If memory is tight, the smallest file is the first one in the table at 0.1 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about LFM2.5 24B A2B
How much VRAM does LFM2.5 24B A2B need?
About 18.1 GB at Q4_K_M with an 8K context window. That is the 15.0 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 LFM2.5 24B A2B on an 8 GB GPU?
Yes, with the smaller files: the 0.1 GB file needs about 3.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of LFM2.5 24B A2B GGUF?
It depends on the quant: file is 0.1 GB, IQ4_XS is 13.3 GB, Q4_K_M is 15.0 GB, Q5_K_M is 17.4 GB.
What context length does LFM2.5 24B A2B support?
The GGUF header lists a trained context length of 131,072 tokens (128K). 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 LFM2.5 24B A2B GGUF?
The files are on Hugging Face in the m9ter1a/LFM2.5-24B-A2B-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 LFM2.5 24B A2B 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.
Can I run LFM2.5 24B A2B on 8 GB VRAM?
Use the IQ4_XS quantization; it requires 16.5 GB memory at 8K context, which is within an 8 GB VRAM budget with efficient batching.
Does this model support vision tasks?
No, it is a text‑only model and does not include vision capabilities.
What is the context length of this model?
The model supports 131,072 tokens of context.