Nemotron 3 Embed 8B BF16 needs about 6.5 GB of memory at Q4_K_M (a 4.9 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 7 quants, from 4.0 GB (Q3_K_M) to 8.5 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 4.6 GB.
8‑Billion‑parameter multilingual embedding model
Nemotron 3 Embed 8B BF16 is a transformer‑based text embedding model with 8 B parameters. It is trained for multilingual retrieval and semantic similarity tasks and supports 34 languages. The model is released under OpenMDW‑1.1 and is ready for commercial use.
Good at
- Multilingual dense retrieval
- Cross‑lingual semantic search
- RAG foundation
Limits
- No vision support
- Requires 262,144‑token context
- OpenMDW‑1.1 license
Best for
- Building multilingual Q&A systems
- Embedding‑based semantic search
- Retrieval‑augmented generation
Who it’s for. Developers and data scientists building multilingual retrieval or RAG pipelines who need a high‑quality embedding model. The model is suitable for enterprise deployments that can accommodate its memory requirements.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q3_K_M | 4.0 GB | 5.7 GB | Fits | Get file → | |
| Q4_K_S | 4.7 GB | 6.3 GB | Fits | Get file → | |
| Q4_K_M | 4.9 GB | 6.5 GB | Fits | Get file → | |
| Q5_K_S | 5.5 GB | 7.2 GB | Fits | Get file → | |
| Q5_K_M | 5.7 GB | 7.3 GB | Tight | Get file → | |
| Q6_K | 6.5 GB | 8.2 GB | Too big | Get file → | |
| Q8_0 | 8.5 GB | 10.1 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_K_M (4.90 GB, ~6.5 GB VRAM at 8k context). If 6 GB VRAM is available, Q4_K_S (4.65 GB) is a good trade‑off. For larger budgets, Q8_0 (8.46 GB) gives the best quality.
What GPU do you need for Nemotron 3 Embed 8B BF16?
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: no quant fits at an 8K context.
- 6 GB VRAM: the best quant that fits is Q3_K_M (4.0 GB file, about 5.7 GB in use).
- 8 GB VRAM: the best quant that fits is Q5_K_M (5.7 GB file, about 7.3 GB in use).
- 12 GB VRAM: the best quant that fits is Q8_0 (8.5 GB file, about 10.1 GB in use).
Which Nemotron 3 Embed 8B BF16 quant should you choose?
Q4_K_M is the usual starting point for Nemotron 3 Embed 8B BF16: it balances file size and quality well. Here it is a 4.9 GB file.
The Q8_0 file is 8.5 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 4.0 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 Nemotron 3 Embed 8B BF16
How much VRAM does Nemotron 3 Embed 8B BF16 need?
About 6.5 GB at Q4_K_M with an 8K context window. That is the 4.9 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 Nemotron 3 Embed 8B BF16 on an 8 GB GPU?
Yes, with Q5_K_M: the 5.7 GB file needs about 7.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Nemotron 3 Embed 8B BF16 GGUF?
It depends on the quant: Q3_K_M is 4.0 GB, Q4_K_S is 4.7 GB, Q4_K_M is 4.9 GB, Q5_K_S is 5.5 GB, Q5_K_M is 5.7 GB, Q6_K is 6.5 GB and 1 more.
What context length does Nemotron 3 Embed 8B BF16 support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.6 GB at 32K.
Where can I download Nemotron 3 Embed 8B BF16 GGUF?
The files are on Hugging Face in the Abiray/Nemotron-3-Embed-8B-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 Nemotron 3 Embed 8B BF16 use?
Hugging Face lists the license as openmdw-1.1. 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 Nemotron 3 Embed 8B on 8 GB VRAM?
Yes, the Q4_K_M quantization is 4.90 GB and requires about 6.5 GB VRAM at 8k context.
Does this model support image inputs?
No, it is a text‑only embedding model.
What license applies to this model?
The model is licensed under OpenMDW‑1.1, with additional Apache 2.0 for third‑party components.