LFM2.5 1.2B Instruct needs about 2.3 GB of memory at Q4_K_M (a 0.7 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 8 quants, from 0.7 GB (Q4_0) to 2.3 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.
LFM2.5 1.2B Instruct – a lightweight, text‑only model for on‑device inference
LFM2.5 1.2B Instruct is a 1.2 B parameter hybrid model built on the LFM2 architecture. It supports a 32,768‑token context and is optimized for edge deployment with fast decoding on CPUs and NPUs. The model is trained with 28 T tokens and includes reinforcement learning.
Good at
- Fast edge inference
- Function calling support
- Agentic and RAG tasks
Limits
- No vision capabilities
- Not suited for knowledge‑intensive or programming tasks
- Requires a 32,768‑token context
Best for
- Agentic task orchestration
- Data extraction workflows
- RAG pipelines
Who it’s for. Developers building lightweight, on‑device chat or agent applications that need function calling and RAG support. The model is suitable for mobile and embedded deployments where memory is limited.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_0 | 0.7 GB | 2.3 GB | Fits | Get file → | |
| Q4_0 | 0.7 GB | 2.3 GB | Fits | Get file → | |
| Q4_K_M | 0.7 GB | 2.3 GB | Fits | Get file → | |
| Q5_K_M | 0.8 GB | 2.4 GB | Fits | Get file → | |
| Q6_K | 1.0 GB | 2.5 GB | Fits | Get file → | |
| Q8_0 | 1.2 GB | 2.8 GB | Fits | Get file → | |
| BF16 | 2.3 GB | 3.9 GB | Fits | Get file → | |
| F16 | 2.3 GB | 3.9 GB | Fits | Get file → |
For 8 GB VRAM, use Q4_0 (0.7 GB file, ~2.3 GB RAM). For 4 GB VRAM, Q4_K_M (0.73 GB) or Q5_K_M (0.84 GB) are suitable. Higher precision quants like Q8_0 or BF16 require more than 8 GB VRAM.
What GPU do you need for LFM2.5 1.2B Instruct?
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 BF16 (2.3 GB file, about 3.9 GB in use).
Which LFM2.5 1.2B Instruct quant should you choose?
Q4_K_M is the usual starting point for LFM2.5 1.2B Instruct: it balances file size and quality well. Here it is a 0.7 GB file.
The Q8_0 file is 1.2 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 Q4_0 at 0.7 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 LFM2.5 1.2B Instruct
How much VRAM does LFM2.5 1.2B Instruct need?
About 2.3 GB at Q4_K_M with an 8K context window. That is the 0.7 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 1.2B Instruct on an 8 GB GPU?
Yes, with BF16: the 2.3 GB file needs about 3.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of LFM2.5 1.2B Instruct GGUF?
It depends on the quant: Q4_0 is 0.7 GB, Q4_0 is 0.7 GB, Q4_K_M is 0.7 GB, Q5_K_M is 0.8 GB, Q6_K is 1.0 GB, Q8_0 is 1.2 GB and 2 more.
What context length does LFM2.5 1.2B Instruct support?
The GGUF header lists a trained context length of 128,000 tokens (125K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.
Where can I download LFM2.5 1.2B Instruct GGUF?
The files are on Hugging Face in the LiquidAI/LFM2.5-1.2B-Instruct-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 1.2B Instruct 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 1.2B Instruct on 4 GB VRAM?
Yes, using Q4_K_M or Q5_K_M quants, which are under 1 GB file size and require about 2.3–2.4 GB RAM at 8k context.
Does the model support image input?
No, LFM2.5 1.2B Instruct is a text‑only model with no vision capabilities.
What inference engines can run this model?
The model is supported by llama.cpp, MLX, and vLLM for fast edge decoding.