LFM2.5-24B-A2B needs about 17.7 GB of memory at Q4_K_M (a 14.5 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 31 quants, from 2.2 GB (IQ2_M) 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 24.0B-parameter model with only 2.45B active parameters per token. It supports a 131,072-token context and is optimized for reasoning and tool‑calling. The model is text‑only and runs efficiently on modern GPUs and Apple silicon.
Good at
- Fast on‑device reasoning
- Efficient tool‑calling
- Large context length
Limits
- No vision support
- Requires 131,072‑token context
- License unspecified
Best for
- Agentic workflows
- Tool‑calling tasks
- Long‑form reasoning
Who it’s for. Developers building private agents that need fast, on‑device reasoning. The model is suitable for applications that benefit from a small active parameter set and a large context window.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ2_M | 2.2 GB | 5.4 GB | Fits | Get file → | |
| Q1_0 | 3.6 GB | 6.8 GB | Fits | Get file → | |
| IQ1_S | 4.9 GB | 8.1 GB | Too big | Get file → | |
| IQ1_M | 5.5 GB | 8.7 GB | Too big | Get file → | |
| IQ2_XXS | 6.4 GB | 9.6 GB | Too big | Get file → | |
| Q2_0 | 6.9 GB | 10.1 GB | Too big | Get file → | |
| IQ2_XS | 7.1 GB | 10.3 GB | Too big | Get file → | |
| IQ2_S | 7.2 GB | 10.3 GB | Too big | Get file → | |
| Q2_K_S | 8.2 GB | 11.4 GB | Too big | Get file → | |
| Q2_K | 8.8 GB | 12.0 GB | Too big | Get file → | |
| IQ3_XXS | 9.3 GB | 12.5 GB | Too big | Get file → | |
| IQ3_XS | 9.9 GB | 13.0 GB | Too big | Get file → | |
| IQ3_S | 10.4 GB | 13.6 GB | Too big | Get file → | |
| Q3_K_S | 10.4 GB | 13.6 GB | Too big | Get file → | |
| IQ3_M | 10.5 GB | 13.7 GB | Too big | Get file → | |
| Q3_K_M | 11.5 GB | 14.7 GB | Too big | Get file → | |
| Q3_K_L | 12.4 GB | 15.6 GB | Too big | Get file → | |
| IQ4_XS | 12.8 GB | 16.0 GB | Too big | Get file → | |
| MXFP4_MOE | 13.3 GB | 16.5 GB | Too big | Get file → | |
| Q4_0 | 13.6 GB | 16.8 GB | Too big | Get file → | |
| IQ4_NL | 13.6 GB | 16.8 GB | Too big | Get file → | |
| Q4_K_S | 13.7 GB | 16.8 GB | Too big | Get file → | |
| Q4_K_M | 14.5 GB | 17.7 GB | Too big | Get file → | |
| Q4_1 | 15.1 GB | 18.2 GB | Too big | Get file → | |
| Q5_0 | 16.5 GB | 19.7 GB | Too big | Get file → | |
| Q5_K_S | 16.5 GB | 19.7 GB | Too big | Get file → | |
| Q5_K_M | 17.0 GB | 20.2 GB | Too big | Get file → | |
| Q5_1 | 18.0 GB | 21.2 GB | Too big | Get file → | |
| Q6_K | 19.7 GB | 22.9 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 (13.66 GB file, ~16.8 GB memory at 8k context). For 12 GB VRAM, Q4_K_M or Q4_K_S (13.66 GB file). For 16 GB VRAM, Q4_0 or Q4_K_M. For 24 GB VRAM, Q6_K or Q8_0. 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: no quant fits at an 8K context.
- 6 GB VRAM: the best quant that fits is IQ2_M (2.2 GB file, about 5.4 GB in use).
- 8 GB VRAM: the best quant that fits is Q1_0 (3.6 GB file, about 6.8 GB in use).
- 12 GB VRAM: the best quant that fits is Q2_K (8.8 GB file, about 12.0 GB in use).
- 16 GB VRAM: the best quant that fits is IQ4_XS (12.8 GB file, about 16.0 GB in use).
- 24 GB VRAM: the best quant that fits is Q6_K (19.7 GB file, about 22.9 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 14.5 GB file.
The Q8_0 file is 25.5 GB, about 1.8 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 IQ2_M at 2.2 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
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 17.7 GB at Q4_K_M with an 8K context window. That is the 14.5 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 Q1_0: the 3.6 GB file needs about 6.8 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: IQ2_M is 2.2 GB, Q1_0 is 3.6 GB, IQ1_S is 4.9 GB, IQ1_M is 5.5 GB, IQ2_XXS is 6.4 GB, Q2_0 is 6.9 GB and 25 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 NANI-Nithin/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.
Can I run LFM2.5-24B-A2B on 8 GB VRAM?
Yes, with the Q4_K_M quantization, which requires about 16.8 GB of memory at 8k context. Ensure sufficient headroom for KV cache and OS.
Does the model support vision inputs?
No, LFM2.5-24B-A2B is a text‑only model and does not process images.
What is the maximum context length?
The model supports up to 131,072 tokens in a single context.