LFM3 VL 2B needs about 3.2 GB of memory at Q4_K_M (a 1.1 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 9 quants, from 0.9 GB (Q3_K_M) to 3.5 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 6.4 GB.
LFM3 VL 2B – 1.92B‑parameter vision‑language model for on‑device visual understanding
LFM3 VL 2B is a 1.92B‑parameter vision‑language model that accepts text, images, and video. It combines a 1.73B‑parameter LFM3 language core with a 164M‑parameter vision encoder and a 25M‑parameter projector. The model supports a 128K‑token context window and native‑resolution video at 2 fps.
Good at
- Multilingual visual reasoning
- Step‑by‑step reasoning for complex visual queries
- Spatial and embodied reasoning for robotics
Limits
- No vision support beyond images and video
- Large memory requirement for full precision
- License is LFM Open License v1.0
Best for
- On‑device visual question answering
- Video analysis in low‑resource environments
- Robotics visual planning
Who it’s for. Developers building on‑device applications that require multilingual visual understanding and step‑by‑step reasoning. The model is suitable for edge devices with sufficient VRAM to run the chosen quantization.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q3_K_M | 0.9 GB | 3.0 GB | Fits | Get file → | |
| Q3_K_L | 1.0 GB | 3.1 GB | Fits | Get file → | |
| Q4_K_S | 1.1 GB | 3.2 GB | Fits | Get file → | |
| Q4_K_M | 1.1 GB | 3.2 GB | Fits | Get file → | |
| Q5_K_S | 1.2 GB | 3.3 GB | Fits | Get file → | |
| Q5_K_M | 1.3 GB | 3.4 GB | Fits | Get file → | |
| Q6_K | 1.4 GB | 3.5 GB | Fits | Get file → | |
| Q8_0 | 1.8 GB | 4.0 GB | Fits | Get file → | |
| BF16 | 3.5 GB | 5.6 GB | Fits | Get file → |
For 8 GB VRAM, use Q4_K_M (file size 1.1 GB, estimated memory 3.2 GB). For 12 GB VRAM, Q5_K_M (1.26 GB, 3.4 GB). For 16 GB VRAM, Q6_K (1.43 GB, 3.5 GB). Higher precision BF16 requires 5.6 GB memory and 3.47 GB file size.
What GPU do you need for LFM3 VL 2B?
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 Q8_0 (1.8 GB file, about 4.0 GB in use).
- 6 GB VRAM: the best quant that fits is BF16 (3.5 GB file, about 5.6 GB in use).
Which LFM3 VL 2B quant should you choose?
Q4_K_M is the usual starting point for LFM3 VL 2B: it balances file size and quality well. Here it is a 1.1 GB file.
The Q8_0 file is 1.8 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_M at 0.9 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 LFM3 VL 2B
How much VRAM does LFM3 VL 2B need?
About 3.2 GB at Q4_K_M with an 8K context window. That is the 1.1 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 LFM3 VL 2B on an 8 GB GPU?
Yes, with BF16: the 3.5 GB file needs about 5.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of LFM3 VL 2B GGUF?
It depends on the quant: Q3_K_M is 0.9 GB, Q3_K_L is 1.0 GB, Q4_K_S is 1.1 GB, Q4_K_M is 1.1 GB, Q5_K_S is 1.2 GB, Q5_K_M is 1.3 GB and 3 more.
What context length does LFM3 VL 2B 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 LFM3 VL 2B GGUF?
The files are on Hugging Face in the prithivMLmods/LFM3-VL-2B-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 LFM3 VL 2B 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 LFM3 VL 2B on 8 GB VRAM?
Yes, using the Q4_K_M quantization which requires approximately 3.2 GB of VRAM at 8 k context.
Does the model support video input?
Yes, it accepts video at native resolution sampled at 2 fps.
What languages are supported?
English, Arabic, Chinese, French, German, Italian, Japanese, Korean, Portuguese, Spanish, Vietnamese, Thai, Indonesian, Hindi, Russian, Polish.