NVIDIA Nemotron 3 Super 120B A12B BF16 — Hardware Requirements & GPU Compatibility
Chat
NVIDIA's Nemotron 3 Super 120B A12B is a mixture-of-experts model with roughly 120 billion total parameters, of which about 12 billion are active for any given token, the figure that primarily drives inference speed. Because the full expert set still needs to be resident in memory, running it locally needs multi-GPU or server-class hardware rather than a single consumer card, even though the active-parameter count keeps generation relatively fast for a model this large. It is tuned for general chat and instruction-following. The model is distributed in bfloat16 precision and supports a 256K token context window. It is released under NVIDIA's own license terms rather than a standard open-source license, and was published on March 10, 2026, as part of the Nemotron 3 series.
1.2M downloads
428 likesSpecifications
- Publisher
- NVIDIA
- Family
- Nemotron
- Parameters
- 123.6B
- Architecture
- NemotronHForCausalLM
- Context Length
- 262,144 tokens
- Vocabulary Size
- 131,072
- Release Date
- 2026-03-10
- License
- Other
Get Started
How Much VRAM Does NVIDIA Nemotron 3 Super 120B A12B BF16 Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| Q2_Kest. | 3.40 | 53.0 GB | 76.5 GB | 52.53 GB | 2-bit quantization with K-quant improvements |
| Q3_K_Mest. | 3.90 | 60.7 GB | 84.2 GB | 60.26 GB | 3-bit medium quantization |
| Q4_K_Mest. | 4.80 | 74.7 GB | 98.1 GB | 74.17 GB | 4-bit medium quantization — most popular sweet spot |
| Q5_K_Mest. | 5.70 | 88.6 GB | 112 GB | 88.07 GB | 5-bit medium quantization — good quality/size tradeoff |
| Q6_Kest. | 6.60 | 102.5 GB | 125.9 GB | 101.98 GB | 6-bit quantization, very good quality |
| Q8_0est. | 8.00 | 124.1 GB | 147.5 GB | 123.61 GB | 8-bit quantization, near-lossless |
| BF16 | 16.00 | 247.7 GB | 271.1 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 BF16?
Q4_K_M · 74.7 GBNVIDIA Nemotron 3 Super 120B A12B 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 262K context window can add up to 23.4 GB, bringing total usage to 98.1 GB. No single GPU has enough memory — multi-GPU or cluster setups are needed.
Which Devices Can Run NVIDIA Nemotron 3 Super 120B A12B BF16?
Q4_K_M · 74.7 GB18 devices with unified memory can run NVIDIA Nemotron 3 Super 120B A12B 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 tightWhere to Download NVIDIA Nemotron 3 Super 120B A12B BF16
Community quantizations of this model — GGUF for llama.cpp, Ollama, and LM Studio, plus AWQ/MLX variants where available.
Benchmarks
Benchmark details →Related Models
Frequently Asked Questions
- How much VRAM does NVIDIA Nemotron 3 Super 120B A12B BF16 need?
NVIDIA Nemotron 3 Super 120B A12B BF16 requires 74.7 GB of VRAM at Q4_K_M, or 247.7 GB at BF16. Full 262K context adds up to 23.4 GB (98.1 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 ≈ 23.9 GB (at full 262K context)
VRAM usage by quantization
Q4_K_M74.7 GBQ4_K_M + full context98.1 GB- Can NVIDIA GeForce RTX 5090 run NVIDIA Nemotron 3 Super 120B A12B BF16?
No — NVIDIA Nemotron 3 Super 120B A12B 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 BF16?
For NVIDIA Nemotron 3 Super 120B A12B 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 BF16 on a Mac?
NVIDIA Nemotron 3 Super 120B A12B 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 BF16 locally?
Yes — NVIDIA Nemotron 3 Super 120B A12B 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 BF16?
At Q4_K_M, NVIDIA Nemotron 3 Super 120B A12B BF16 can reach ~52 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 = ~160 tok/s
Estimated speed at Q4_K_M (74.7 GB)
~160 tok/s~160 tok/s~141 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 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 BF16?
No single consumer GPU has enough VRAM to run NVIDIA Nemotron 3 Super 120B A12B 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 BF16?
19 devices with unified memory can run NVIDIA Nemotron 3 Super 120B A12B 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.