Nemotron SEA LION v4.8 30B A3B needs about 33.0 GB of memory at Q4_K_M (a 25.4 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 11 quants, from 18.7 GB (Q2_K) to 35.0 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 28.5 GB.
Nemotron SEA LION v4.8 30B A3B – a 32.9B parameter Mixture of Experts LLM
Nemotron SEA LION v4.8 30B A3B is a 32.9B parameter instruction‑tuned model built on a Mixture of Experts architecture. It supports 1,048,576 token context and is trained on Southeast Asian languages. The model is released under the MIT license.
Good at
- Reasoning
- Tool usage
- Multilingual instruction following
Limits
- Large VRAM requirement
- No vision support
- No GPU acceleration beyond llama.cpp
Best for
- Chatbots needing long context
- Research on Southeast Asian languages
- Tool‑integrated assistants
Who it’s for. Developers building multilingual chat or research tools that require deep reasoning and tool integration. The model is suitable for users with access to sufficient GPU memory to run the chosen quantization.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 18.7 GB | 26.3 GB | Too big | Get file → | |
| Q3_K_S | 18.7 GB | 26.3 GB | Too big | Get file → | |
| IQ4_XS | 19.0 GB | 26.6 GB | Too big | Get file → | |
| Q3_K_M | 20.7 GB | 28.3 GB | Too big | Get file → | |
| Q3_K_L | 21.6 GB | 29.2 GB | Too big | Get file → | |
| Q4_K_S | 22.8 GB | 30.4 GB | Too big | Get file → | |
| Q5_K_S | 24.8 GB | 32.4 GB | Too big | Get file → | |
| Q4_K_M | 25.4 GB | 33.0 GB | Too big | Get file → | |
| Q5_K_M | 27.0 GB | 34.7 GB | Too big | Get file → | |
| Q6_K | 34.9 GB | 42.5 GB | Too big | Get file → | |
| Q8_0 | 35.0 GB | 42.6 GB | Too big | Get file → |
For 8 GB VRAM, use Q2_K (18.66 GB file, ~26.3 GB RAM at 8k context). For 12 GB VRAM, Q3_K_S (18.68 GB file, ~26.3 GB RAM). For 16 GB VRAM, Q4_K_S (22.84 GB file, ~30.4 GB RAM). Memory estimates are approximate.
What GPU do you need for Nemotron SEA LION v4.8 30B A3B?
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: no quant fits at an 8K context.
- 8 GB VRAM: no quant fits at an 8K context.
- 12 GB VRAM: no quant fits at an 8K context.
- 16 GB VRAM: no quant fits at an 8K context.
- 24 GB VRAM: no quant fits at an 8K context.
- 32 GB VRAM: the best quant that fits is Q4_K_S (22.8 GB file, about 30.4 GB in use).
- 48 GB VRAM: the best quant that fits is Q8_0 (35.0 GB file, about 42.6 GB in use).
Which Nemotron SEA LION v4.8 30B A3B quant should you choose?
Q4_K_M is the usual starting point for Nemotron SEA LION v4.8 30B A3B: it balances file size and quality well. Here it is a 25.4 GB file.
The Q8_0 file is 35.0 GB, about 1.4 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 18.7 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
Frequently asked questions about Nemotron SEA LION v4.8 30B A3B
How much VRAM does Nemotron SEA LION v4.8 30B A3B need?
About 33.0 GB at Q4_K_M with an 8K context window. That is the 25.4 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 SEA LION v4.8 30B A3B on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 26.3 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Nemotron SEA LION v4.8 30B A3B GGUF?
It depends on the quant: Q2_K is 18.7 GB, Q3_K_S is 18.7 GB, IQ4_XS is 19.0 GB, Q3_K_M is 20.7 GB, Q3_K_L is 21.6 GB, Q4_K_S is 22.8 GB and 5 more.
What context length does Nemotron SEA LION v4.8 30B A3B support?
The GGUF header lists a trained context length of 1,048,576 tokens (1024K). The KV cache grows with the context you use: about 7.1 GB at 8K and 28.5 GB at 32K.
Where can I download Nemotron SEA LION v4.8 30B A3B GGUF?
The files are on Hugging Face in the mradermacher/Nemotron-SEA-LION-v4.8-30B-A3B-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 SEA LION v4.8 30B A3B use?
Hugging Face lists the license as mit. 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, with the Q2_K quant, which requires about 26.3 GB of RAM at 8k context.
Does this model support vision tasks?
No, the model does not include vision capabilities.
What license does the model use?
The model is released under the MIT license.