NVIDIA Nemotron 3 Ultra 550B A55B Base BF16 — Hardware Requirements & GPU Compatibility
Chat
NVIDIA Nemotron 3 Ultra 550B A55B Base BF16 is a 560.5B-parameter open language model from NVIDIA in the Nemotron family. It supports a context window of up to 262,144 tokens. At Q4_K_M it needs about 369.95 GB of VRAM — see which GPUs and Macs can run it below.
NVIDIA Nemotron 3 Ultra 550B A55B Base BF16 runs on a 512 GB+ Mac or a multi-GPU server
Best local pick → Mac Studio (M3 Ultra, 512GB) · Q4_K_M · 378.4 GB · ~13 tok/s
Macs from 512 GB (Q4_K_M · ~13 tok/s)
Other
Not set up for it?
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run NVIDIA Nemotron 3 Ultra 550B A55B Base BF16
One recommended way. Every other method, OS and quant is in the step-by-step guide.
Recommended
vllm serve nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-Base-BF16 --max-model-len 16384 --tensor-parallel-size 8Size the nodes from the table above
Download: Weights on Hugging Face
Other ways
each opens step-by-stepRun in cloud
Rent 6× H100 SXM · Q4_K_M
- Estimated hourly price
- ~$13.27/hr
- est., whole server
- GPUs
- 6 GPUs
- 480 GB of VRAM
How Much VRAM Does NVIDIA Nemotron 3 Ultra 550B A55B Base BF16 Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | Runs on | |
|---|---|---|---|---|
| 262.1 GB | 280.1 GB | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Runs on Instinct MI350X 288 GB | |
| 300.6 GB | 318.7 GB | 3-bit medium — 3-bit medium quantization | Runs on 5× H100 SXM 80 GB | |
| 369.9 GB | 388 GB | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Runs on 6× H100 SXM 80 GB | |
| 439.3 GB | 457.4 GB | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Runs on 7× H100 SXM 80 GB | |
| 508.7 GB | 526.8 GB | 6-bit, very good — 6-bit quantization, very good quality | Runs on 8× H100 SXM 80 GB | |
| 616.6 GB | 634.7 GB | 8-bit, near-lossless — 8-bit quantization, near-lossless | Runs on 5× H200 SXM 141 GB | |
| 1233.2 GB | 1251.2 GB | 16-bit · bfloat — Brain floating point 16 — preferred for training | Runs on 8× B200 192 GB |
Selected Q4_K_M
4-bit medium quantization378.4GBat 16K context
- Weights
- 368.5 GB
- KV cache
- 9.6 GB
- Overhead
- 0.3 GB
Server-class: ~378.4 GB at 16K context · about 6× H100 SXM 80 GB
Which Hardware Can Run NVIDIA Nemotron 3 Ultra 550B A55B Base BF16?
Q4_K_M · 369.9 GBNVIDIA Nemotron 3 Ultra 550B A55B Base BF16 (Q4_K_M) requires 369.9 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 481+ GB is recommended. No consumer GPU has enough memory. 1 device with unified memory can run NVIDIA Nemotron 3 Ultra 550B A55B Base BF16, including Mac Studio (M3 Ultra, 512GB).
Needs server-class hardware
NVIDIA Nemotron 3 Ultra 550B A55B Base BF16 runs on a 512 GB+ Mac or a multi-GPU server · Q4_K_M needs ~378.4 GB
| Hardware | Quant | Memory | Speed | Context | Hardware page | |
|---|---|---|---|---|---|---|
| Mac 512 GB · Mac Studio (M3 Ultra, 512GB) | Q4_K_M | 378.4 GB | ~13 tok/s | 128K ctx | Mac Studio → | Q4_K_M · 378.4 GB · ~13 tok/s · 128K ctx |
| 6× H100 SXM 80 GB · 480 GB | Q4_K_M | 378.4 GB | — | 64K ctx | H100 SXM → | Q4_K_M · 378.4 GB · 64K ctx |
| 3× H200 SXM 141 GB · 423 GB | Q4_K_M | 378.4 GB | — | 16K ctx | H200 SXM → | Q4_K_M · 378.4 GB · 16K ctx |
| 3× B200 192 GB · 576 GB | Q4_K_M | 378.4 GB | — | 128K ctx | B200 → | Q4_K_M · 378.4 GB · 128K ctx |
Also: Mac Studio (M3 Ultra, 512GB) · NVIDIA DGX A100 640GB · NVIDIA DGX H100
By VRAM tier · typical GPUs and Macs at Q4_K_M
Consumer GPUs (up to 32 GB) and Macs up to 256 GB: too small for this model (needs ≥ 270.5 GB)8 GB tier →12 GB tier →16 GB tier →24 GB tier →Macs →
Alternatives to NVIDIA Nemotron 3 Ultra 550B A55B Base BF16
Nemotron family · 42 models →Similar models
2| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| Ling 3.1 FlashInclusion AI | — | 344.9 GB | —needs > 24 GB | same size |
| LongCat Flash ChatMeituan | — | 1244.5 GB | —needs > 24 GB | same size |
Fine-tunes & variants(1)
Specifications
- Publisher
- NVIDIA
- Family
- Nemotron
- Parameters
- 560.5B
- Active parameters
- 57B per token
- Architecture
- NemotronHForCausalLM
- Context Length
- 262,144 tokens
- Vocabulary Size
- 131,072
- Release Date
- 2026-06-03
- License
- Other
Frequently Asked Questions
How much VRAM does NVIDIA Nemotron 3 Ultra 550B A55B Base BF16 need?
NVIDIA Nemotron 3 Ultra 550B A55B Base BF16 requires 369.9 GB of VRAM at Q4_K_M, or 1233.2 GB at BF16.
VRAM = Weights + KV Cache + Overhead
Weights = 560.5B × 4.8 bits ÷ 8 = 336.3 GB
KV Cache + Overhead ≈ 33.6 GB (at 2K context + ~0.3 GB framework)
Fit ratings and hardware model lists check this model with room for a 16K-token context, which needs a little more memory.
VRAM usage by quantization
Can NVIDIA GeForce RTX 5090 run NVIDIA Nemotron 3 Ultra 550B A55B Base BF16?
No — NVIDIA Nemotron 3 Ultra 550B A55B Base BF16 requires at least 262.1 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 Ultra 550B A55B Base BF16?
For NVIDIA Nemotron 3 Ultra 550B A55B Base BF16, Q4_K_M (369.9 GB) offers the best balance of quality and VRAM usage. Q5_K_M (439.3 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 262.1 GB.
VRAM requirement by quantization
★ Recommended — best balance of quality and VRAM usage.
Can I run NVIDIA Nemotron 3 Ultra 550B A55B Base BF16 on a Mac?
Yes — Mac Studio (M3 Ultra, 512GB) and above can run NVIDIA Nemotron 3 Ultra 550B A55B Base BF16. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 369.9 GB of usable unified memory (RAM minus macOS overhead).
Can I run NVIDIA Nemotron 3 Ultra 550B A55B Base BF16 locally?
Yes — NVIDIA Nemotron 3 Ultra 550B A55B Base BF16 can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
What's the download size of NVIDIA Nemotron 3 Ultra 550B A55B Base BF16?
At Q4_K_M, the download is about 336.31 GB. The full-precision BF16 version is 1121.05 GB. The smallest option (Q2_K) is 238.22 GB.
Which GPUs can run NVIDIA Nemotron 3 Ultra 550B A55B Base BF16?
No single consumer GPU has enough VRAM to run NVIDIA Nemotron 3 Ultra 550B A55B Base BF16 at Q4_K_M (369.9 GB). Multi-GPU or professional hardware is required.
Which devices can run NVIDIA Nemotron 3 Ultra 550B A55B Base BF16?
1 device with unified memory can run NVIDIA Nemotron 3 Ultra 550B A55B Base BF16 at Q4_K_M (369.9 GB), including Mac Studio (M3 Ultra, 512GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.