Nemotron Ultra 253B
NVIDIA · dense · 253B parameters · 131,072 context
Parameters
253B
Context Window
128K tokens
Architecture
Dense
Best GPU
B200 NVL (pair)
Cheapest API
$6.00/M
Quality Score
86/100
Intelligence Brief
Nemotron Ultra 253B is a 253B parameter DENSE model from NVIDIA, featuring Grouped Query Attention (GQA) with 96 layers and 12,288 hidden dimensions. With a 131,072 token context window, it supports tools, structured output, code, math, multilingual, reasoning. On standardized benchmarks, it achieves MMLU 90, HumanEval 76, GSM8K 94. The most cost-effective API deployment is via nvidia at $6.00/M output tokens. For self-hosted inference, B200 NVL (pair) delivers optimal throughput at $9965/month.
Architecture Details
Memory Requirements
BF16 Weights
506.0 GB
FP8 Weights
253.0 GB
INT4 Weights
126.5 GB
Fits on (single GPU) — most practical first
Fits on (multi-GPU with Tensor Parallelism)
Multi-GPU configurations use Tensor Parallelism (TP) to split model layers across GPUs. Requires NVLink or NVSwitch interconnect for optimal performance.
GPU Compatibility Matrix
Nemotron Ultra 253B is compatible with 8% of GPU configurations across 41 GPUs at 3 precision levels.
GPU Recommendations
FP8 · 1 GPU · tensorrt-llm
93/100
score
Throughput
280.0 tok/s
Latency (ITL)
3.6ms
Est. TTFT
1ms
Cost/Month
$9965
Cost/M Tokens
$13.54
FP8 · 4 GPUs · tensorrt-llm
90/100
score
Throughput
280.0 tok/s
Latency (ITL)
3.6ms
Est. TTFT
1ms
Cost/Month
$3758
Cost/M Tokens
$5.11
FP8 · 2 GPUs · tensorrt-llm
88/100
score
Throughput
280.0 tok/s
Latency (ITL)
3.6ms
Est. TTFT
1ms
Cost/Month
$8522
Cost/M Tokens
$11.58
Deployment Options
API Deployment
nvidia
$6.00/M
output tokens
Single GPU
B200 NVL (pair)
$9965/mo
Min VRAM: 253 GB
Multi-GPU
H20 x4
280.0 tok/s
TP· $3758/mo
API Pricing Comparison
| Provider | Input $/M | Output $/M | Badges |
|---|---|---|---|
| nvidia | $2.00 | $6.00 | Cheapest |
Cost Analysis
| Provider | Input $/M | Output $/M | ~Monthly Cost |
|---|---|---|---|
| nvidiaBest Value | $2.00 | $6.00 | $40 |
Cost per 1,000 Requests
Short (500 tok)
$2.20
via nvidia
Medium (2K tok)
$8.80
via nvidia
Long (8K tok)
$28.00
via nvidia
Performance Estimates
Throughput by GPU
VRAM Breakdown (B200 NVL (pair), FP8)
Precision Impact
bf16
506.0 GB
weights/GPU
fp8
253.0 GB
weights/GPU
~280.0 tok/s
int4
126.5 GB
weights/GPU
Quality Benchmarks
Capabilities
Features
Supported Frameworks
Supported Precisions
Where to Deploy Nemotron Ultra 253B
Similar Models
Nemotron 340B
340B params · dense
Quality: 85
from $4.20/M
Nemotron-3 Super 120B
120B params · dense
Quality: 84
from $2.40/M
DeepSeek Coder V2 236B
236B params · moe
Quality: 50
from $0.28/M
DeepSeek V2.5
236B params · moe
Quality: 78
from $0.28/M
Qwen 3 235B
235B params · moe
Quality: 83
from $3.00/M
Frequently Asked Questions
How much VRAM does Nemotron Ultra 253B need for inference?
Nemotron Ultra 253B requires approximately 506.0 GB of VRAM at BF16 precision, 253.0 GB at FP8, or 126.5 GB at INT4 quantization. Additional VRAM is needed for KV-cache (393216 bytes per token) and activations (~5.00 GB).
What is the best GPU for Nemotron Ultra 253B?
The top recommended GPU for Nemotron Ultra 253B is the B200 NVL (pair) using FP8 precision. It achieves approximately 280.0 tokens/sec at an estimated cost of $9965/month ($13.54/M tokens). Score: 93/100.
How much does Nemotron Ultra 253B inference cost?
Nemotron Ultra 253B API inference starts from $2.00/M input tokens and $6.00/M output tokens. Self-hosted inference costs depend on your GPU configuration — use our ROI calculator for a detailed breakdown.