NVIDIA Nemotron 3 Super 120B A12B MLX 9bit — Hardware Requirements & GPU Compatibility
Chat
2.2K downloads
3 likesSpecifications
- Publisher
- inferencerlabs
- Parameters
- 120.7B
- Architecture
- NemotronHForCausalLM
- Context Length
- 262,144 tokens
- Vocabulary Size
- 131,072
- Release Date
- 2026-03-14
Get Started
How Much VRAM Does NVIDIA Nemotron 3 Super 120B A12B MLX 9bit Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| BF16 | 16.00 | 241.8 GB | 265.3 GB | 241.34 GB | Brain floating point 16 — preferred for training |
Which GPUs Can Run NVIDIA Nemotron 3 Super 120B A12B MLX 9bit?
BF16 · 241.8 GBNVIDIA Nemotron 3 Super 120B A12B MLX 9bit (BF16) requires 241.8 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 315+ GB is recommended. Using the full 262K context window can add up to 23.4 GB, bringing total usage to 265.3 GB. No single GPU has enough memory — multi-GPU or cluster setups are needed.
Which Devices Can Run NVIDIA Nemotron 3 Super 120B A12B MLX 9bit?
BF16 · 241.8 GB2 devices with unified memory can run NVIDIA Nemotron 3 Super 120B A12B MLX 9bit, including NVIDIA DGX H100, NVIDIA DGX A100 640GB.
Runs great
— Plenty of headroomRelated Models
Frequently Asked Questions
- How much VRAM does NVIDIA Nemotron 3 Super 120B A12B MLX 9bit need?
NVIDIA Nemotron 3 Super 120B A12B MLX 9bit requires 241.8 GB of VRAM at BF16. Full 262K context adds up to 23.4 GB (265.3 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 120.7B × 16 bits ÷ 8 = 241.3 GB
KV Cache + Overhead ≈ 0.5 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 24 GB (at full 262K context)
VRAM usage by quantization
BF16241.8 GBBF16 + full context265.3 GB- Can NVIDIA GeForce RTX 5090 run NVIDIA Nemotron 3 Super 120B A12B MLX 9bit?
No — NVIDIA Nemotron 3 Super 120B A12B MLX 9bit requires at least 241.8 GB at BF16, which exceeds the NVIDIA GeForce RTX 5090's 32 GB of VRAM.
- Can I run NVIDIA Nemotron 3 Super 120B A12B MLX 9bit on a Mac?
NVIDIA Nemotron 3 Super 120B A12B MLX 9bit requires at least 241.8 GB at BF16, which exceeds the unified memory of most consumer Macs. You would need a Mac Studio or Mac Pro with a high-memory configuration.
- Can I run NVIDIA Nemotron 3 Super 120B A12B MLX 9bit locally?
Yes — NVIDIA Nemotron 3 Super 120B A12B MLX 9bit can run locally on consumer hardware. At BF16 quantization it needs 241.8 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- What's the download size of NVIDIA Nemotron 3 Super 120B A12B MLX 9bit?
At BF16, the download is about 241.34 GB.
- Which GPUs can run NVIDIA Nemotron 3 Super 120B A12B MLX 9bit?
No single consumer GPU has enough VRAM to run NVIDIA Nemotron 3 Super 120B A12B MLX 9bit at BF16 (241.8 GB). Multi-GPU or professional hardware is required.
- Which devices can run NVIDIA Nemotron 3 Super 120B A12B MLX 9bit?
2 devices with unified memory can run NVIDIA Nemotron 3 Super 120B A12B MLX 9bit at BF16 (241.8 GB), including NVIDIA DGX A100 640GB, NVIDIA DGX H100. Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.