Nemotron-SEA-LION-v4.8-120B-A12B
Nemotron-SEA-LION-v4.8-120B-A12B is an open-weight language model from AI Singapore with 124B parameters (mixture of experts). At 4-bit it needs about 82.4 GB of memory, so the smallest current device that fits it is the RTX PRO 6000 Blackwell.
Overview
Includes room for an 8k context and runtime overhead. More context needs more memory.
Key information
- Lab
- AI Singapore
- Released
- 8 Sep 2026
- Parameters
- 124B · MoE
- Type
- Language
- Context
- 262,144 tokens
- License
- MIT
- HF downloads, 30 days
- 409
More from AI Singapore
View allWill it run on your hardware?
How we estimate| Estimate or device | Memory |
|---|---|
| Q4 | 82.4 GB |
| Q8 | 144.9 GB |
| BF16 | 272.8 GB |
| RTX 5060 Ti 16 GB | 16 GB usable |
| RTX 5090 32 GB | 32 GB usable |
| DGX Spark 128 GB | 108.8 GB usable |
| Mac Studio M5 Ultra 256 GB | 192 GB usable |
Single-device memory estimate. Pick a device to update the On your device column.
36 GB usable memory
| Format | Memory needed | On your device | Example hardware |
|---|---|---|---|
| 4-bit (Q4) | ≈ 82.4 GB | Too big 229% | RTX PRO 6000 Blackwell96 GB memory |
| 8-bit (Q8) | ≈ 144.9 GB | Too big 403% | Mac Studio M5 Ultra (256GB)256 GB memory |
| 16-bit (BF16) | ≈ 272.8 GB | Too big 758% | Mac Studio M3 Ultra (512GB)Discontinued512 GB memory |
Fits means the estimate stays within 90% of usable memory. Tight is above 90% and up to 100%. Too big is above 100%. These are memory checks, not speed or compatibility tests.
Mac allowances are 66% of total RAM up to 36 GB, and 75% above. AI boxes allow 85% because their memory is shared with the operating system.
Where to run it
Through an API
No hosted API found.
More about this model
Frequently asked questions
How much memory does Nemotron-SEA-LION-v4.8-120B-A12B need? At an 8k context, about 82.4 GB at 4-bit, 144.9 GB at 8-bit and 272.8 GB at 16-bit (BF16). A longer context needs more.
Can I run Nemotron-SEA-LION-v4.8-120B-A12B on a Mac? The smallest current Mac that fits the 4-bit estimate of 82.4 GB is the Mac Studio M5 Max (128GB). We have not found a trusted MLX or GGUF build yet.
Does the full context fit? Nemotron-SEA-LION-v4.8-120B-A12B supports up to 262,144 tokens of context. Our memory estimates use 8k, so long prompts need more memory than shown.
What does it cost through an API? We did not find a hosted API for this model.
License in plain English
MIT. This license permits commercial use, modification and redistribution, as long as the copyright and license notice are kept. This summary is not legal advice.
OMHQ RigBench
Not yet tested. We show no speed or quality score without a measurement.
Revision history and sources
Last updated . Sources:Hugging Face model card.