LFM2.5 Embedding 350M needs about 1.3 GB of memory at Q4_K_M (a 0.2 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 7 quants, from 0.2 GB (Q4_0) to 0.7 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 2.1 GB.
Dense bi‑encoder for fast multilingual retrieval
LFM2.5 Embedding 350M is a 350 million‑parameter dense bi‑encoder. It generates one vector per document for cross‑lingual search across 11 languages. The model supports a 512‑token context and is optimized for speed and low memory usage.
Good at
- Fast multilingual document retrieval
- Low‑memory inference
- Single‑vector indexing
Limits
- Requires 512‑token context
- No vision or audio support
- License type is other
Best for
- E‑commerce product search
- FAQ and support knowledge bases
- On‑device semantic search
Who it’s for. Engineers building retrieval‑augmented generation pipelines or local semantic search solutions. Suitable for applications needing quick, multilingual document ranking with limited GPU memory.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_0 | 0.2 GB | 1.3 GB | Fits | Get file → | |
| Q4_K_M | 0.2 GB | 1.3 GB | Fits | Get file → | |
| Q5_K_M | 0.3 GB | 1.3 GB | Fits | Get file → | |
| Q6_K | 0.3 GB | 1.3 GB | Fits | Get file → | |
| Q8_0 | 0.4 GB | 1.4 GB | Fits | Get file → | |
| BF16 | 0.7 GB | 1.7 GB | Fits | Get file → | |
| F16 | 0.7 GB | 1.7 GB | Fits | Get file → |
For 8 GB VRAM, use Q4_0 or Q4_K_M (≈1.3 GB memory at 8k context). If 16 GB VRAM is available, Q5_K_M or Q6_K are also suitable. Higher precision quants (BF16, F16) need more than 1.7 GB memory and are best for larger GPUs.
What GPU do you need for LFM2.5 Embedding 350M?
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 (0.7 GB file, about 1.7 GB in use).
Which LFM2.5 Embedding 350M quant should you choose?
Q4_K_M is the usual starting point for LFM2.5 Embedding 350M: it balances file size and quality well. Here it is a 0.2 GB file.
The Q8_0 file is 0.4 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 0.2 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 Embedding 350M
How much VRAM does LFM2.5 Embedding 350M need?
About 1.3 GB at Q4_K_M with an 8K context window. That is the 0.2 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 Embedding 350M on an 8 GB GPU?
Yes, with BF16: the 0.7 GB file needs about 1.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of LFM2.5 Embedding 350M GGUF?
It depends on the quant: Q4_0 is 0.2 GB, Q4_K_M is 0.2 GB, Q5_K_M is 0.3 GB, Q6_K is 0.3 GB, Q8_0 is 0.4 GB, BF16 is 0.7 GB and 1 more.
What context length does LFM2.5 Embedding 350M support?
The GGUF header lists a trained context length of 128,000 tokens (125K). The KV cache grows with the context you use: about 0.5 GB at 8K and 2.1 GB at 32K.
Where can I download LFM2.5 Embedding 350M GGUF?
The files are on Hugging Face in the LiquidAI/LFM2.5-Embedding-350M-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 Embedding 350M 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 Embedding 350M on 8 GB VRAM?
Yes, the Q4_0 or Q4_K_M quantizations use about 1.3 GB of VRAM at 8k context, fitting comfortably on 8 GB GPUs.
Does the model support image inputs?
No, the model is a text‑only dense bi‑encoder and does not process visual data.
What languages does it support?
English, Spanish, German, French, Italian, Portuguese, Arabic, Swedish, Norwegian, Japanese, and Korean.