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 10 quants, from 1.3 GB (Q3_K_S) to 5.4 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 8.1 GB.
LFM2.5 VL 3B – multimodal, on‑device vision‑language model
LFM2.5 VL 3B is a 2.7B parameter hybrid model that processes text and images. It uses a SigLIP2 NaFlex vision encoder and supports a 32,768‑token context window across 16 languages. The model is optimized for single‑turn, high‑throughput tasks such as OCR and on‑device translation.
Good at
- Vision‑language grounding
- Full‑page OCR with layout
- Low‑latency inference on mobile
Limits
- Not suited for long‑context reasoning
- No vision support beyond images
- Requires 3.3 GB+ memory for full performance
Best for
- Near‑real‑time object detection
- Batch OCR of scanned documents
- On‑device menu translation
Who it’s for. Developers building lightweight, on‑device vision‑language applications that need fast, single‑turn inference. The model is ideal for mobile or embedded systems where memory and latency are critical.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| 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_L | 1.5 GB | 4.0 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 → | |
| Q5_K_S | 1.9 GB | 4.4 GB | Fits | Get file → | |
| Q5_K_M | 1.9 GB | 4.5 GB | Fits | Get file → | |
| Q8_0 | 2.9 GB | 5.4 GB | Fits | Get file → | |
| BF16 | 5.4 GB | 7.9 GB | Tight | Get file → | |
| F16 | 5.4 GB | 7.9 GB | Tight | Get file → |
For 8 GB VRAM, use Q4_K_M (1.67 GB file, ~4.2 GB memory). For 4 GB VRAM, use Q3_K_S (1.27 GB file, ~3.8 GB memory). For higher quality with 12 GB VRAM, use Q5_K_M (1.94 GB file, ~4.5 GB memory).
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 Q3_K_L (1.5 GB file, about 4.0 GB in use).
- 6 GB VRAM: the best quant that fits is Q8_0 (2.9 GB file, about 5.4 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 Q3_K_S at 1.3 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
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: Q3_K_S is 1.3 GB, Q3_K_M is 1.4 GB, Q3_K_L is 1.5 GB, Q4_K_S is 1.6 GB, Q4_K_M is 1.7 GB, Q5_K_S is 1.9 GB and 4 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 prithivMLmods/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 apache-2.0. 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, the Q4_K_M quant uses about 4.2 GB memory at 8 k context, fitting within 8 GB VRAM.
Does the model support image generation?
No, the model only processes images for understanding, not generation.
What license applies to the GGUF files?
The GGUF files are released under the Apache‑2.0 license.