Skip to content
Bitpute

How much VRAM does Nemotron Ultra 253B Instruct need?

By Bitpute · Published 12 July 2026 · Updated 24 July 2026 · How we estimate · Sources · Editorial policy · Version history · Report an error · Figures re-checked against the calculation engine on every build

Nemotron Ultra 253B Instruct needs about 150.7 GB of VRAM at Q4_K_M, or 263.6 GB at Q8_0 and 495.6 GB at FP16. No single GPU in our set holds it even at Q4_K_M; it needs multi-GPU or offload. Weights plus runtime overhead. Budget separately for KV cache, which at 128K is a material share.

Weights-plus-runtime footprint across the six most common quantizations. KV cache is context-dependent and comes on top. At 128K it is gigabytes on its own, before the weights; size it precisely in the GPU Memory Calculator.

Parameters253B
Context128K
VendorNVIDIA
LicenseOpen weights (see card)
Released2024

Can your GPU run Nemotron Ultra 253B Instruct?

Pick your card — the answer below is computed by the same engine that produces every figure on this page.

No — not enough VRAM
Estimated VRAM150.7 GB
GPU VRAM141 GB
Short by16.8 GB

H200 141GB cannot hold Nemotron Ultra 253B Instruct at Q4_K_M: it needs 150.7 GB against 133.9 GB usable; a heavier quantization, a larger card, or splitting across GPUs are the ways forward.

Weights plus runtime overhead. KV cache is not included — it depends on context length and this model’s published architecture.

Why
Weights (Q4_K_M)142.8 GB
Runtime overhead7.9 GB
Estimated total150.7 GB
Usable VRAM (95% of 141 GB)133.9 GB

Across every GPU we track

Estimates, not guarantees: real usage moves with runtime, driver, batch size and context. Size a specific context window in the GPU Memory Calculator.

How was this number calculated? Every figure here comes from Bitpute’s documented calculation methodology — parameters, precision, quantization, runtime overhead and usable VRAM, each formula written out in full.

Memory by quantization

QuantWeights+ runtime overhead
FP16471.2 GB495.6 GB
Q8_0250.4 GB263.6 GB
Q6_K193.2 GB203.6 GB
Q5_K_M167.6 GB176.7 GB
Q4_K_M142.8 GB150.7 GB
Q4_0132.5 GB139.9 GB

Overhead = 0.75 GB + 5% of weights (CUDA context, buffers). Add KV cache on top. Weights dominate at this size, but a 128K window still costs gigabytes.

Which quantization should you actually run?

Nemotron Ultra 253B Instruct is a multi-GPU or datacenter model: even Q4_K_M needs about 150.7 GB, beyond any single card. Plan for several 80 GB GPUs or a hosted endpoint; FP16 (495.6 GB) is server-only.

Single-GPU fit at Q4_K_M (150.7 GB + KV)

RTX 3060 12GBRTX 4060 Ti 16GBRTX 4070 Ti SUPERRTX 3090RTX 4090RTX 5090A100 40GBRTX A6000L40SA100 80GBH100 80GBH200 141GB

Size it exactly →Rent a GPU for it →

Common questions

How much VRAM does Nemotron Ultra 253B Instruct need?

Nemotron Ultra 253B Instruct needs about 150.7 GB of VRAM at Q4_K_M, 263.6 GB at Q8_0, or 495.6 GB at FP16. That is weights plus about 0.75 GB of runtime overhead and 5% of weight size; KV cache is additional and depends on context length.

What GPU can run Nemotron Ultra 253B Instruct?

No single GPU in our set fits it at Q4_K_M; it needs multiple GPUs or CPU offload. At FP16 no single GPU in our set is sufficient.

Can Nemotron Ultra 253B Instruct run on 24 GB?

Not at Q4_K_M: it needs about 150.7 GB, more than the ~22.8 GB usable on a 24 GB card. Use a larger card, multiple GPUs, or offload.

More in the Nemotron family

Nemotron Nano 9B v2 InstructNemotron Super 49B InstructNemotron Llama-3.1 51B InstructNemotron Llama-3.1 70B InstructNemotron 4 340B Instruct