LFM2.5 24B A2B needs about 16.8 GB of memory at its main file (a 13.6 GB file) with an 8K context window, so it fits on a 24 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 10.7 GB.
24B-parameter reasoning model with 2B active parameters for fast on-device agents
LFM2.5‑24B‑A2B is a 24.0B‑parameter reasoning model with only 2.45B active parameters. It supports a 131,072‑token context and is optimized for agentic and tool‑use tasks.
Good at
- Agentic reasoning
- Tool‑calling
- Fast on‑device inference
Limits
- No vision support
- Requires high VRAM (~16.8 GB at 8 k context)
- Large context length may limit deployment on low‑memory devices
Best for
- On‑device private agents
- Tool‑enabled assistants
- Long‑context reasoning
Who it’s for. Developers building private, fast agents that need reasoning and tool‑calling capabilities on local hardware. It is ideal for applications requiring high throughput and low active parameter usage.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 13.6 GB | 16.8 GB | Too big | Get file → |
The available GGUF file is 13.58 GB and requires approximately 16.8 GB of VRAM at 8 k context. This is the only quant available, so use it if your hardware can accommodate the memory requirement.
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: 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 the main file (13.6 GB file, about 16.8 GB in use).
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 16.8 GB at its main file with an 8K context window. That is the 13.6 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?
Not at an 8K context. The smallest file needs about 16.8 GB, so you would need a larger GPU or CPU offloading.
What is the file size of LFM2.5 24B A2B GGUF?
It depends on the quant: file is 13.6 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 WhiskyAKM/LFM2.5-24B-A2B-NVFP4-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?
No, the model requires about 16.8 GB of VRAM at 8 k context, which exceeds 8 GB.
Is LFM2.5‑24B‑A2B compatible with llama.cpp?
Yes, the GGUF file is designed for use with llama.cpp and other GGUF‑compatible inference engines.
Does LFM2.5‑24B‑A2B support vision tasks?
No, it is a text‑only reasoning model and does not support vision.