nomic-embed-text-v2-moe needs about 1.1 GB of memory at Q4_K_M (a 0.3 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 15 quants, from 0.3 GB (Q2_K) to 1.9 GB (F32).
Multilingual Mixture of Experts text embedding model
nomic-embed-text-v2-moe is a 475M parameter MoE model for multilingual text embeddings. It supports up to 512 tokens and flexible embedding dimensions from 768 to 256. The model is fully open‑source under Apache‑2.0.
Good at
- High multilingual retrieval performance
- Efficient embedding with Matryoshka representation
- Supports many languages
Limits
- Requires 8‑k context for memory estimates
- No vision or generation capabilities
- Active parameters 305M during inference
Best for
- Embedding for retrieval‑augmented generation
- Multilingual semantic search
- Embedding pipelines with limited GPU memory
Who it’s for. Developers building multilingual search or RAG systems who need efficient embeddings. The model is suitable for users with GPU memory budgets as low as 1 GB for low‑precision quantizations.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 0.3 GB | 0.8 GB | Fits | Get file → | |
| Q3_K_S | 0.3 GB | 0.8 GB | Fits | Get file → | |
| Q3_K_M | 0.3 GB | 0.8 GB | Fits | Get file → | |
| Q3_K_L | 0.3 GB | 0.8 GB | Fits | Get file → | |
| Q4_0 | 0.3 GB | 0.8 GB | Fits | Get file → | |
| Q4_K_S | 0.3 GB | 0.8 GB | Fits | Get file → | |
| Q4_1 | 0.3 GB | 0.9 GB | Fits | Get file → | |
| Q4_K_M | 0.3 GB | 0.9 GB | Fits | Get file → | |
| Q5_K_S | 0.4 GB | 0.9 GB | Fits | Get file → | |
| Q5_K_M | 0.4 GB | 0.9 GB | Fits | Get file → | |
| Q6_K | 0.4 GB | 0.9 GB | Fits | Get file → | |
| Q8_0 | 0.5 GB | 1.0 GB | Fits | Get file → | |
| BF16 | 1.0 GB | 1.5 GB | Fits | Get file → | |
| F16 | 1.0 GB | 1.5 GB | Fits | Get file → | |
| F32 | 1.9 GB | 2.4 GB | Fits | Get file → |
For 1 GB VRAM, use Q2_K (0.27 GB) or Q3_K_S (0.29 GB). For 2 GB VRAM, Q4_K_M (0.34 GB) or Q5_K_M (0.37 GB) are suitable. Higher precision Q8_0 (0.51 GB) or BF16 (0.96 GB) requires more memory but offers better quality.
What GPU do you need for nomic-embed-text-v2-moe?
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 F32 (1.9 GB file, about 2.7 GB in use).
Which nomic-embed-text-v2-moe quant should you choose?
Q4_K_M is the usual starting point for nomic-embed-text-v2-moe: it balances file size and quality well. Here it is a 0.3 GB file.
The Q8_0 file is 0.5 GB, about 1.5 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 0.3 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 nomic-embed-text-v2-moe
How much VRAM does nomic-embed-text-v2-moe need?
About 1.1 GB at Q4_K_M with an 8K context window. That is the 0.3 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 nomic-embed-text-v2-moe on an 8 GB GPU?
Yes, with F32: the 1.9 GB file needs about 2.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of nomic-embed-text-v2-moe GGUF?
It depends on the quant: Q2_K is 0.3 GB, Q3_K_S is 0.3 GB, Q3_K_M is 0.3 GB, Q3_K_L is 0.3 GB, Q4_0 is 0.3 GB, Q4_K_S is 0.3 GB and 9 more.
What context length does nomic-embed-text-v2-moe support?
The GGUF header lists a trained context length of 512 tokens (512). The KV cache grows with the context you use: about 0.3 GB at 8K and 0.0 GB at 512.
Where can I download nomic-embed-text-v2-moe GGUF?
The files are on Hugging Face in the nomic-ai/nomic-embed-text-v2-moe-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 nomic-embed-text-v2-moe 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 Q2_K on 1 GB VRAM?
Yes, Q2_K is 0.27 GB and estimated to use 1.1 GB at 8k context.
Does this model support image input?
No, it only provides text embedding capabilities.
What license does it use?
Apache‑2.0, fully open‑source.