Lfm2.5-Vl-3B needs about 4.2 GB of memory at Q4_K_M (a 1.7 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 21 quants, from 1.0 GB (IQ2_M) to 5.4 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 8.1 GB.
Multimodal LFM2.5-VL-3B for on‑device vision and text tasks
LFM2.5-VL-3B is a multimodal variant of LFM2.5. It processes text and images using a LFM2.5-2.6B backbone and a SigLIP2 NaFlex vision encoder. The model supports up to 32,768 context tokens and is optimized for low‑latency inference on device.
Good at
- Efficient vision‑text grounding
- Full‑page OCR with layout annotation
- Low‑latency single‑turn inference
Limits
- Not suited for long‑context reasoning
- Requires 3.3 GB+ memory for full model
- No support for languages beyond the listed 16
Best for
- Real‑time object detection in automotive
- Batch OCR of scanned documents
- On‑device translation of menus and signs
Who it’s for. Developers building on‑device applications that need both vision and text understanding. The model is suitable for mobile, embedded, or edge devices where low latency and moderate memory usage are critical.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ2_M | 1.0 GB | 3.5 GB | Fits | Get file → | |
| Q2_K_XL | 1.1 GB | 3.6 GB | Fits | Get file → | |
| IQ3_XXS | 1.1 GB | 3.7 GB | Fits | Get file → | |
| Q3_K_S | 1.3 GB | 3.8 GB | Fits | Get file → | |
| Q3_K_M | 1.4 GB | 3.9 GB | Fits | Get file → | |
| Q3_K_XL | 1.4 GB | 3.9 GB | Fits | Get file → | |
| IQ4_XS | 1.5 GB | 4.0 GB | Fits | Get file → | |
| IQ4_NL | 1.6 GB | 4.1 GB | Fits | Get file → | |
| Q4_0 | 1.6 GB | 4.1 GB | Fits | Get file → | |
| Q4_K_S | 1.6 GB | 4.1 GB | Fits | Get file → | |
| Q4_K_M | 1.7 GB | 4.2 GB | Fits | Get file → | |
| Q4_K_XL | 1.7 GB | 4.2 GB | Fits | Get file → | |
| Q4_1 | 1.7 GB | 4.3 GB | Fits | Get file → | |
| Q5_K_S | 1.9 GB | 4.4 GB | Fits | Get file → | |
| Q5_K_M | 1.9 GB | 4.5 GB | Fits | Get file → | |
| Q5_K_XL | 1.9 GB | 4.5 GB | Fits | Get file → | |
| Q6_K | 2.2 GB | 4.7 GB | Fits | Get file → | |
| Q6_K_XL | 2.4 GB | 4.9 GB | Fits | Get file → | |
| Q8_0 | 2.9 GB | 5.4 GB | Fits | Get file → | |
| Q8_K_XL | 3.4 GB | 6.0 GB | Fits | Get file → | |
| BF16 | 5.4 GB | 7.9 GB | Tight | Get file → |
For 8 GB VRAM, use Q4_K_M (1.67 GB, 4.2 GB memory). For 12 GB VRAM, Q5_K_M (1.94 GB, 4.5 GB memory) is a good balance. For 16 GB VRAM, Q6_K (2.22 GB, 4.7 GB memory) offers higher precision.
What GPU do you need for Lfm2.5-Vl-3B?
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 IQ4_XS (1.5 GB file, about 4.0 GB in use).
- 6 GB VRAM: the best quant that fits is Q8_K_XL (3.4 GB file, about 6.0 GB in use).
- 8 GB VRAM: the best quant that fits is BF16 (5.4 GB file, about 7.9 GB in use).
Which Lfm2.5-Vl-3B quant should you choose?
Q4_K_M is the usual starting point for Lfm2.5-Vl-3B: it balances file size and quality well. Here it is a 1.7 GB file.
The Q8_0 file is 2.9 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 IQ2_M at 1.0 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-Vl-3B
How much VRAM does Lfm2.5-Vl-3B need?
About 4.2 GB at Q4_K_M with an 8K context window. That is the 1.7 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-Vl-3B on an 8 GB GPU?
Yes, with BF16: the 5.4 GB file needs about 7.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Lfm2.5-Vl-3B GGUF?
It depends on the quant: IQ2_M is 1.0 GB, Q2_K_XL is 1.1 GB, IQ3_XXS is 1.1 GB, Q3_K_S is 1.3 GB, Q3_K_M is 1.4 GB, Q3_K_XL is 1.4 GB and 15 more.
What context length does Lfm2.5-Vl-3B support?
The GGUF header lists a trained context length of 128,000 tokens (125K). The KV cache grows with the context you use: about 2.0 GB at 8K and 8.1 GB at 32K.
Where can I download Lfm2.5-Vl-3B GGUF?
The files are on Hugging Face in the unsloth/LFM2.5-VL-3B-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-Vl-3B 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-VL-3B on 8 GB VRAM?
Yes, using a Q4_K_M quantized model which requires approximately 4.2 GB of VRAM at 8k context.
Does the model support OCR?
Yes, it provides full‑page OCR with layout annotation using the SigLIP2 NaFlex encoder.
What is the maximum context length?
The model supports up to 32,768 tokens of context.