Most Embed De needs about 1.8 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 12 quants, from 0.5 GB (Q2_K) to 2.3 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 2.1 GB.
German embedding model for retrieval in customer‑support
Most Embed De is a 1.14B‑parameter embedding model fine‑tuned for German retrieval tasks. It supports up to 262144 context tokens and is optimized for customer‑support RAG systems. The model is available in multiple GGUF quantizations.
Good at
- German text retrieval
- Embedding generation
- Support RAG systems
Limits
- No vision support
- CC‑BY‑NC‑4.0 license
- Requires GPU for inference
Best for
- FAQ search engines
- Help‑center document lookup
- Retrieval‑augmented chatbots
Who it’s for. Developers building German‑language retrieval systems or customer‑support applications. The model is suitable for teams that need high‑quality embeddings on commodity GPUs.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 0.5 GB | 1.6 GB | Fits | Get file → | |
| Q3_K_S | 0.6 GB | 1.6 GB | Fits | Get file → | |
| Q3_K_M | 0.6 GB | 1.7 GB | Fits | Get file → | |
| Q3_K_L | 0.7 GB | 1.7 GB | Fits | Get file → | |
| IQ4_XS | 0.7 GB | 1.7 GB | Fits | Get file → | |
| Q4_K_S | 0.7 GB | 1.8 GB | Fits | Get file → | |
| Q4_K_M | 0.7 GB | 1.8 GB | Fits | Get file → | |
| Q5_K_S | 0.8 GB | 1.9 GB | Fits | Get file → | |
| Q5_K_M | 0.8 GB | 1.9 GB | Fits | Get file → | |
| Q6_K | 0.9 GB | 2.0 GB | Fits | Get file → | |
| Q8_0 | 1.2 GB | 2.3 GB | Fits | Get file → | |
| F16 | 2.3 GB | 3.3 GB | Fits | Get file → |
For 8 GB VRAM, use Q4_K_M (0.75 GB file, ~1.8 GB memory). For 12 GB VRAM, Q5_K_M (0.84 GB file, ~1.9 GB memory) or Q6_K (0.94 GB file, ~2 GB memory). For larger budgets, Q8_0 (1.22 GB file, ~2.3 GB memory) or F16 (2.29 GB file, ~3.3 GB memory) provide higher precision.
What GPU do you need for Most Embed De?
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 F16 (2.3 GB file, about 3.3 GB in use).
Which Most Embed De quant should you choose?
Q4_K_M is the usual starting point for Most Embed De: it balances file size and quality well. Here it is a 0.7 GB file.
The Q8_0 file is 1.2 GB, about 1.6 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 Q2_K at 0.5 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 Most Embed De
How much VRAM does Most Embed De need?
About 1.8 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 Most Embed De on an 8 GB GPU?
Yes, with F16: the 2.3 GB file needs about 3.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Most Embed De GGUF?
It depends on the quant: Q2_K is 0.5 GB, Q3_K_S is 0.6 GB, Q3_K_M is 0.6 GB, Q3_K_L is 0.7 GB, IQ4_XS is 0.7 GB, Q4_K_S is 0.7 GB and 6 more.
What context length does Most Embed De support?
The GGUF header lists a trained context length of 262,144 tokens (256K). 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 Most Embed De GGUF?
The files are on Hugging Face in the mradermacher/most-embed-de-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 Most Embed De use?
Hugging Face lists the license as cc-by-nc-4.0. 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 this model on 8 GB VRAM?
Yes, the Q4_K_M quant requires about 1.8 GB VRAM at 8k context, which fits in 8 GB.
Does the model support other languages besides German?
The base model supports many languages, but the embedding model is optimized for German retrieval.
Is the model free to use?
It is licensed under CC‑BY‑NC‑4.0, so it can be used for non‑commercial purposes.