NVIDIA Nemotron 3 Super 120B A12B Base BF16 — Hardware Requirements & GPU Compatibility
Chat
NVIDIA Nemotron 3 Super 120B A12B Base BF16 is a 123.6B-parameter open language model from NVIDIA in the Nemotron family. It supports a context window of up to 1,048,576 tokens. At Q4_K_M it needs about 74.65 GB of VRAM — see which GPUs and Macs can run it below.
3.8K downloads
19 likesSpecifications
- Publisher
- NVIDIA
- Family
- Nemotron
- Parameters
- 123.6B
- Architecture
- NemotronHForCausalLM
- Context Length
- 1,048,576 tokens
- Vocabulary Size
- 131,072
- Release Date
- 2026-03-10
- License
- Other
Get Started
How Much VRAM Does NVIDIA Nemotron 3 Super 120B A12B Base BF16 Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| Q2_Kest. | 3.40 | 53.0 GB | 147.3 GB | 52.53 GB | 2-bit quantization with K-quant improvements |
| Q3_K_Mest. | 3.90 | 60.7 GB | 155.1 GB | 60.26 GB | 3-bit medium quantization |
| Q4_K_Mest. | 4.80 | 74.7 GB | 169.0 GB | 74.17 GB | 4-bit medium quantization — most popular sweet spot |
| Q5_K_Mest. | 5.70 | 88.6 GB | 182.9 GB | 88.07 GB | 5-bit medium quantization — good quality/size tradeoff |
| Q6_Kest. | 6.60 | 102.5 GB | 196.8 GB | 101.98 GB | 6-bit quantization, very good quality |
| Q8_0est. | 8.00 | 124.1 GB | 218.4 GB | 123.61 GB | 8-bit quantization, near-lossless |
| BF16est. | 16.00 | 247.7 GB | 342.0 GB | 247.22 GB | Brain floating point 16 — preferred for training |
est.= calculated VRAM estimate; no published GGUF file found for that quantization yet. Other rows are verified against real community uploads.
Which GPUs Can Run NVIDIA Nemotron 3 Super 120B A12B Base BF16?
Q4_K_M · 74.7 GBNVIDIA Nemotron 3 Super 120B A12B Base BF16 (Q4_K_M) requires 74.7 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 98+ GB is recommended. Using the full 1049K context window can add up to 94.3 GB, bringing total usage to 169.0 GB. No single GPU has enough memory — multi-GPU or cluster setups are needed.
Which Devices Can Run NVIDIA Nemotron 3 Super 120B A12B Base BF16?
Q4_K_M · 74.7 GB18 devices with unified memory can run NVIDIA Nemotron 3 Super 120B A12B Base BF16, including NVIDIA DGX H100, NVIDIA DGX A100 640GB, Asus ROG Flow Z13 (2025, Ryzen AI Max+ 395, 128 GB).
Runs great
— Plenty of headroom
Decent
— Enough memory, may be tightRelated Models
Frequently Asked Questions
- How much VRAM does NVIDIA Nemotron 3 Super 120B A12B Base BF16 need?
NVIDIA Nemotron 3 Super 120B A12B Base BF16 requires 74.7 GB of VRAM at Q4_K_M, or 247.7 GB at BF16. Full 1049K context adds up to 94.3 GB (169.0 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 123.6B × 4.8 bits ÷ 8 = 74.2 GB
KV Cache + Overhead ≈ 0.5 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 94.8 GB (at full 1049K context)
VRAM usage by quantization
Q4_K_M74.7 GBQ4_K_M + full context169.0 GB- Can NVIDIA GeForce RTX 5090 run NVIDIA Nemotron 3 Super 120B A12B Base BF16?
No — NVIDIA Nemotron 3 Super 120B A12B Base BF16 requires at least 53.0 GB at Q2_K, which exceeds the NVIDIA GeForce RTX 5090's 32 GB of VRAM.
- What's the best quantization for NVIDIA Nemotron 3 Super 120B A12B Base BF16?
For NVIDIA Nemotron 3 Super 120B A12B Base BF16, Q4_K_M (74.7 GB) offers the best balance of quality and VRAM usage. Q5_K_M (88.6 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 53.0 GB.
VRAM requirement by quantization
Q2_K53.0 GBQ4_K_M ★74.7 GBQ5_K_M88.6 GBQ6_K102.5 GBQ8_0124.1 GBBF16247.7 GB★ Recommended — best balance of quality and VRAM usage.
- Can I run NVIDIA Nemotron 3 Super 120B A12B Base BF16 on a Mac?
NVIDIA Nemotron 3 Super 120B A12B Base BF16 requires at least 53.0 GB at Q2_K, 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 Base BF16 locally?
Yes — NVIDIA Nemotron 3 Super 120B A12B Base BF16 can run locally on consumer hardware. At Q4_K_M quantization it needs 74.7 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is NVIDIA Nemotron 3 Super 120B A12B Base BF16?
At Q4_K_M, NVIDIA Nemotron 3 Super 120B A12B Base BF16 can reach ~59 tok/s on AMD Instinct MI350X. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.
tok/s = (bandwidth GB/s ÷ model GB) × efficiency
Example: NVIDIA B200 → 8000 ÷ 74.7 × 0.65 = ~70 tok/s
Estimated speed at Q4_K_M (74.7 GB)
~70 tok/s~70 tok/s~59 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of NVIDIA Nemotron 3 Super 120B A12B Base BF16?
At Q4_K_M, the download is about 74.17 GB. The full-precision BF16 version is 247.22 GB. The smallest option (Q2_K) is 52.53 GB.
- Which GPUs can run NVIDIA Nemotron 3 Super 120B A12B Base BF16?
No single consumer GPU has enough VRAM to run NVIDIA Nemotron 3 Super 120B A12B Base BF16 at Q4_K_M (74.7 GB). Multi-GPU or professional hardware is required.
- Which devices can run NVIDIA Nemotron 3 Super 120B A12B Base BF16?
19 devices with unified memory can run NVIDIA Nemotron 3 Super 120B A12B Base BF16 at Q4_K_M (74.7 GB), including ASUS Ascent GX10, Asus ROG Flow Z13 (2025, Ryzen AI Max+ 395, 128 GB), Beelink GTR9 Pro (Ryzen AI Max+ 395, 128 GB), Framework Desktop (Ryzen AI Max+ 395, 128 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.