LFM2 8B A1B needs about 7.2 GB of memory at Q4_K_M (a 5.0 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 6 quants, from 4.7 GB (Q4_0) to 16.7 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 6.4 GB.
LFM2 8B A1B – a small‑size MoE model for on‑device use
LFM2 8B A1B is a mixture‑of‑experts model with 8.3 B total parameters and 1.5 B active parameters. It is designed for edge AI and runs efficiently on phones, tablets and laptops. The model supports English, Arabic, Chinese, French, German, Japanese, Korean and Spanish.
Good at
- Agentic tasks
- Data extraction
- RAG
Limits
- No vision support
- Not suited for knowledge‑intensive or programming tasks
- Requires 8 k context for memory estimates
Best for
- On‑device chat agents
- Narrow‑domain fine‑tuning
- Creative writing
Who it’s for. Developers building lightweight agents or assistants that run locally on consumer devices. The model is ideal for teams that need fast inference and low memory usage while maintaining reasonable quality.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_0 | 4.7 GB | 6.8 GB | Fits | Get file → | |
| Q4_K_M | 5.0 GB | 7.2 GB | Fits | Get file → | |
| Q5_K_M | 5.9 GB | 8.0 GB | Too big | Get file → | |
| Q6_K | 6.8 GB | 9.0 GB | Too big | Get file → | |
| Q8_0 | 8.9 GB | 11.0 GB | Too big | Get file → | |
| F16 | 16.7 GB | 18.8 GB | Too big | Get file → |
For 8 GB VRAM, Q4_0 (4.73 GB) or Q4_K_M (5.04 GB) are suitable, using about 6.8–7.2 GB memory at 8 k context. If 12 GB VRAM is available, Q5_K_M (5.92 GB) or Q6_K (6.85 GB) provide higher quality. Larger Q8_0 or F16 variants need 16–18 GB VRAM and are not recommended for edge devices.
What GPU do you need for LFM2 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: no quant fits at an 8K context.
- 8 GB VRAM: the best quant that fits is Q5_K_M (5.9 GB file, about 8.0 GB in use).
- 12 GB VRAM: the best quant that fits is Q8_0 (8.9 GB file, about 11.0 GB in use).
- 16 GB VRAM: the best quant that fits is Q8_0 (8.9 GB file, about 11.0 GB in use).
- 24 GB VRAM: the best quant that fits is F16 (16.7 GB file, about 18.8 GB in use).
Which LFM2 8B A1B quant should you choose?
Q4_K_M is the usual starting point for LFM2 8B A1B: it balances file size and quality well. Here it is a 5.0 GB file.
The Q8_0 file is 8.9 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 Q4_0 at 4.7 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about LFM2 8B A1B
How much VRAM does LFM2 8B A1B need?
About 7.2 GB at Q4_K_M with an 8K context window. That is the 5.0 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 8B A1B on an 8 GB GPU?
Yes, with Q5_K_M: the 5.9 GB file needs about 8.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of LFM2 8B A1B GGUF?
It depends on the quant: Q4_0 is 4.7 GB, Q4_K_M is 5.0 GB, Q5_K_M is 5.9 GB, Q6_K is 6.8 GB, Q8_0 is 8.9 GB, F16 is 16.7 GB.
What context length does LFM2 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 8B A1B GGUF?
The files are on Hugging Face in the LiquidAI/LFM2-8B-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 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 8B A1B on a laptop with 8 GB VRAM?
Yes, the Q4_0 or Q4_K_M quantized files fit within 8 GB VRAM, using roughly 6.8–7.2 GB at 8 k context.
Does LFM2 8B A1B support image input?
No, the model has no vision capability.
What languages can LFM2 8B A1B understand?
It supports English, Arabic, Chinese, French, German, Japanese, Korean and Spanish.