Lfm2.5-8B-A1B needs about 7.4 GB of memory at Q4_K_M (a 5.3 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 22 quants, from 2.6 GB (IQ1_M) to 16.9 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 6.4 GB.
8‑B hybrid LFM model for on‑device agentic tasks
Lfm2.5‑8B‑A1B is a general‑purpose text‑only model with 8.3 B total parameters and 1.5 B active parameters. It supports a 128 k token context and is optimized for on‑device inference with llama.cpp, MLX, vLLM and SGLang.
Good at
- Agentic workflows
- Tool calling
- Multilingual assistance
Limits
- Large context requires high VRAM
- Not ideal for heavy programming or knowledge‑intensive QA without retrieval
- No vision support
Best for
- Personal‑assistant apps
- Structured output generation
- Tool‑enabled chatbots
Who it’s for. Developers building lightweight, on‑device assistants that need reasoning and tool use. Suitable for mobile or edge deployments where GPU memory is limited.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_M | 2.6 GB | 4.7 GB | Fits | Get file → | |
| IQ2_XXS | 2.7 GB | 4.8 GB | Fits | Get file → | |
| IQ2_M | 2.8 GB | 4.9 GB | Fits | Get file → | |
| Q2_K_XL | 2.9 GB | 5.0 GB | Fits | Get file → | |
| IQ3_XXS | 3.3 GB | 5.4 GB | Fits | Get file → | |
| IQ3_S | 3.6 GB | 5.7 GB | Fits | Get file → | |
| Q3_K_M | 3.9 GB | 6.1 GB | Fits | Get file → | |
| Q3_K_XL | 4.0 GB | 6.1 GB | Fits | Get file → | |
| IQ4_XS | 4.3 GB | 6.4 GB | Fits | Get file → | |
| IQ4_NL | 4.4 GB | 6.5 GB | Fits | Get file → | |
| Q4_K_S | 5.0 GB | 7.1 GB | Fits | Get file → | |
| Q4_K_M | 5.3 GB | 7.4 GB | Tight | Get file → | |
| MXFP4_MOE | 5.3 GB | 7.5 GB | Tight | Get file → | |
| Q4_K_XL | 5.4 GB | 7.5 GB | Tight | Get file → | |
| Q5_K_S | 6.0 GB | 8.1 GB | Too big | Get file → | |
| Q5_K_M | 6.4 GB | 8.5 GB | Too big | Get file → | |
| Q5_K_XL | 6.4 GB | 8.5 GB | Too big | Get file → | |
| Q6_K | 7.1 GB | 9.2 GB | Too big | Get file → | |
| Q6_K_XL | 7.7 GB | 9.9 GB | Too big | Get file → | |
| Q8_0 | 9.0 GB | 11.1 GB | Too big | Get file → | |
| Q8_K_XL | 9.3 GB | 11.5 GB | Too big | Get file → | |
| BF16 | 16.9 GB | 19.1 GB | Too big | Get file → |
For 8 GB VRAM, use IQ4_XS (4.26 GB, ~6.4 GB VRAM at 8 k context). For 12 GB VRAM, Q4_K_M (5.32 GB, ~7.4 GB VRAM) or MXFP4_MOE (5.35 GB, ~7.5 GB VRAM). Higher‑quality quants such as Q5_K_M (6.36 GB, ~8.5 GB VRAM) fit 16 GB VRAM setups.
What GPU do you need for Lfm2.5-8B-A1B?
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 IQ3_S (3.6 GB file, about 5.7 GB in use).
- 8 GB VRAM: the best quant that fits is Q4_K_XL (5.4 GB file, about 7.5 GB in use).
- 12 GB VRAM: the best quant that fits is Q8_K_XL (9.3 GB file, about 11.5 GB in use).
- 16 GB VRAM: the best quant that fits is Q8_K_XL (9.3 GB file, about 11.5 GB in use).
- 24 GB VRAM: the best quant that fits is BF16 (16.9 GB file, about 19.1 GB in use).
Which Lfm2.5-8B-A1B quant should you choose?
Q4_K_M is the usual starting point for Lfm2.5-8B-A1B: it balances file size and quality well. Here it is a 5.3 GB file.
The Q8_0 file is 9.0 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 IQ1_M at 2.6 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 Lfm2.5-8B-A1B
How much VRAM does Lfm2.5-8B-A1B need?
About 7.4 GB at Q4_K_M with an 8K context window. That is the 5.3 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 Lfm2.5-8B-A1B on an 8 GB GPU?
Yes, with Q4_K_XL: the 5.4 GB file needs about 7.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Lfm2.5-8B-A1B GGUF?
It depends on the quant: IQ1_M is 2.6 GB, IQ2_XXS is 2.7 GB, IQ2_M is 2.8 GB, Q2_K_XL is 2.9 GB, IQ3_XXS is 3.3 GB, IQ3_S is 3.6 GB and 16 more.
What context length does Lfm2.5-8B-A1B support?
The GGUF header lists a trained context length of 128,000 tokens (125K). The KV cache grows with the context you use: about 1.6 GB at 8K and 6.4 GB at 32K.
Where can I download Lfm2.5-8B-A1B GGUF?
The files are on Hugging Face in the unsloth/LFM2.5-8B-A1B-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 Lfm2.5-8B-A1B 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 Lfm2.5‑8B‑A1B on 8 GB VRAM?
Yes, with the IQ4_XS quant it uses about 6.4 GB VRAM at 8 k context, leaving headroom for other processes.
Does the model support image input?
No, it is a text‑only model and does not process vision data.
What is the maximum context length?
The model supports up to 128,000 tokens of context.