LFM2.5 24B A2B needs about 18.5 GB of memory at Q4_K_M (a 15.4 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 25 quants, from 0.1 GB to 48.0 GB (BF16). 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 text‑only reasoning model with 24 billion total parameters and 2.45 billion active parameters. It supports a 131 072‑token context and is optimized for on‑device inference with llama.cpp. The model excels at agentic tasks and tool calling.
Good at
- Fast on‑device reasoning
- Efficient MoE inference
- Tool‑calling support
Limits
- Large context length requires high VRAM
- No vision or audio input
- License is other, not open source
Best for
- Building private reasoning agents
- Tool‑enabled chatbots
- On‑device inference on high‑VRAM GPUs
Who it’s for. Developers building private, fast reasoning agents that run locally. The model is suitable for applications needing reliable tool use and reasoning without external knowledge bases.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.1 GB | 3.3 GB | Fits | Get file → | |
| IQ2_XS | 7.5 GB | 10.7 GB | Too big | Get file → | |
| IQ2_S | 8.0 GB | 11.1 GB | Too big | Get file → | |
| IQ2_M | 8.8 GB | 12.0 GB | Too big | Get file → | |
| Q2_K | 9.2 GB | 12.4 GB | Too big | Get file → | |
| IQ3_XXS | 10.3 GB | 13.5 GB | Too big | Get file → | |
| IQ3_XS | 10.9 GB | 14.1 GB | Too big | Get file → | |
| Q3_K_S | 11.0 GB | 14.2 GB | Too big | Get file → | |
| Q3_K_M | 11.6 GB | 14.7 GB | Too big | Get file → | |
| Q3_K_L | 12.2 GB | 15.4 GB | Too big | Get file → | |
| IQ3_M | 12.6 GB | 15.8 GB | Too big | Get file → | |
| IQ4_XS | 13.4 GB | 16.6 GB | Too big | Get file → | |
| Q4_0 | 13.6 GB | 16.8 GB | Too big | Get file → | |
| Q4_K_S | 14.3 GB | 17.5 GB | Too big | Get file → | |
| Q4_1 | 15.1 GB | 18.3 GB | Too big | Get file → | |
| IQ4_NL | 15.2 GB | 18.4 GB | Too big | Get file → | |
| Q4_K_M | 15.4 GB | 18.5 GB | Too big | Get file → | |
| Q4_K_L | 16.4 GB | 19.6 GB | Too big | Get file → | |
| Q5_K_S | 17.2 GB | 20.4 GB | Too big | Get file → | |
| Q5_K_M | 18.5 GB | 21.7 GB | Too big | Get file → | |
| Q6_K_S | 20.2 GB | 23.4 GB | Too big | Get file → | |
| Q6_K | 21.2 GB | 24.3 GB | Too big | Get file → | |
| Q6_K_L | 22.2 GB | 25.4 GB | Too big | Get file → | |
| Q8_0 | 25.5 GB | 28.7 GB | Too big | Get file → | |
| BF16 | 48.0 GB | 51.1 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_K_M (15.35 GB file, ~18.5 GB memory at 8k context). For 12 GB VRAM, Q4_K_L (16.37 GB file, ~19.6 GB memory). For 16 GB VRAM, Q5_K_S (17.19 GB file, ~20.4 GB memory). Estimates are approximate.
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 IQ2_M (8.8 GB file, about 12.0 GB in use).
- 16 GB VRAM: the best quant that fits is IQ3_M (12.6 GB file, about 15.8 GB in use).
- 24 GB VRAM: the best quant that fits is Q6_K_S (20.2 GB file, about 23.4 GB in use).
- 32 GB VRAM: the best quant that fits is Q8_0 (25.5 GB file, about 28.7 GB in use).
- 48 GB VRAM: the best quant that fits is Q8_0 (25.5 GB file, about 28.7 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 15.4 GB file.
The Q8_0 file is 25.5 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
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 18.5 GB at Q4_K_M with an 8K context window. That is the 15.4 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, IQ2_XS is 7.5 GB, IQ2_S is 8.0 GB, IQ2_M is 8.8 GB, Q2_K is 9.2 GB, IQ3_XXS is 10.3 GB and 19 more.
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 bartowski/LiquidAI_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?
Only with a low‑precision quant like Q4_K_M, which requires about 18.5 GB memory at 8k context. 8 GB VRAM is insufficient for full inference.
Does the model support image input?
No, the model is text‑only and does not support vision or audio.
What is the context length of this model?
The model supports a context length of 131,072 tokens.