Will It Run AI

Can Nemotron 70B run on RTX PRO 6000 Blackwell Server Edition 96GB?

YES — Runs Great

A73Great
Estimated from fit model

Nemotron 70B needs ~58.1 GB VRAM. RTX PRO 6000 Blackwell Server Edition 96GB has 96.0 GB. With Q4_K_M quantization, expect ~31 tok/s.

Runtime: llama.cppCapacity: RoomyBandwidth: HighStack: StandardBottleneck: Balanced
Share:

Operating mode

Choose the run profile you care about

Interactive favors responsiveness, while light API and scale-out lean harder on serving readiness. The fit stays the same, but the recommendation lens changes.

Current mode

Balanced

Balanced for general local use. Keeps the ranking neutral across personal and serving workflows.

Capabilities:

Select quantization to explore

Q4_K_M (Medium quality) — 58.1 GB, 34.2 tok/s, Runs well
58.1 GB required96.0 GB available
61% VRAM used

Fit status

Runs well

Decode

34.2 tok/s

TTFT

5667 ms

Safe context

131K

Memory

58.1 GB / 96.0 GB

Memory breakdown

Weights42.7 GB
KV Cache4.9 GB
Runtime0.9 GB
Headroom9.6 GB

See how fast it feels

See how fast it feelsNemotron 70B on RTX PRO 6000 Blackwell Server Edition 96GB
1st promptCold start — includes initialization
>Solve: If a train travels at 60 mph for 2.5 hours, how far does it go?
Let me work through this step by step. Given information: - Speed = 60 mph (miles per hour) - Time = 2.5 hours Formula: Distance = Speed x Time Calculation: Distance = 60 mph x 2.5 h = 150 miles The train travels 150 miles. Double-check: at 60 mph the train covers 60 miles each hour. In half an hour it covers 30 miles. So in 2.5 hours: 60 + 60 + 30 = 150 miles. Confirmed.
2nd promptWarm — model ready, no init overhead
>What if the train stops for 20 minutes halfway?
The stop doesn't change the total distance covered while moving, but it affects total trip time. Breakdown: - First half: 1.25 hours at 60 mph = 75 miles - Stop: 20 minutes (no distance) - Second half: 1.25 hours at 60 mph = 75 miles Total distance: 150 miles (same) Total time: 2.5 h + 0.33 h = 2.83 hours Average speed: 150 / 2.83 = 53 mph The distance stays the same but average speed drops to 53 mph because of the stop.
Estimated: 34.2 tok/s decode · 5.7s TTFT (warm) · 85 tok/s prefill

What limits this setup

This setup is broadly balanced for this model.

No major red flags

This recommendation has enough memory headroom and acceptable estimated speed for the selected workload.

Best improvement path

Performance by workload

WorkloadGradeFitDecodeTTFTContext
ChatARuns well31.4 tok/s3361 ms131K
CodingARuns well31.4 tok/s6162 ms131K
Agentic CodingARuns well31.4 tok/s8963 ms131K
ReasoningARuns well31.4 tok/s7283 ms131K
RAGARuns well34.2 tok/s10303 ms131K

Quantization options

How Nemotron 70B (70B params) fits at each quantization level on RTX PRO 6000 Blackwell Server Edition 96GB (96.0 GB usable).

QuantBitsVRAMQualityFit
Q2_K
2
27.3 GB
LowB64
Q3_K_S
3
34.3 GB
LowB65
NVFP4
4
39.2 GB
MediumB67
Q4_K_M
4
42.7 GB
MediumB67
Q5_K_M
5
50.4 GB
HighB69
Q6_K
6
57.4 GB
HighB69
Q8_0Best for your GPU
8
74.9 GB
Very HighB69
F16
16
143.5 GB
MaximumF0

Get started

Copy-paste commands to run Nemotron 70B on your machine.

Run

ollama run nemotron

Your hardware

More models your RTX PRO 6000 Blackwell Server Edition 96GB can run

ModelParamsGradeDecodeCapabilities
MistralDevstral 2 123B Instruct123BS19.4 tok/s
AlibabaQwen 3.5 122B A10B122BS53.9 tok/s
MistralMistral Small 4 119B119BS58.5 tok/s
OpenAIGPT-OSS 120B117BS20.4 tok/s
CohereCommand A 111B111BS21.6 tok/s

Frequently asked questions

Can RTX PRO 6000 Blackwell Server Edition 96GB run Nemotron 70B?

Yes, RTX PRO 6000 Blackwell Server Edition 96GB can run Nemotron 70B with a A grade (Runs well). Expected decode speed: 31.4 tok/s.

How much VRAM does Nemotron 70B need?

Nemotron 70B (70B parameters) requires approximately 58.1 GB of memory with Q4_K_M quantization.

What is the best quantization for Nemotron 70B?

The recommended quantization for Nemotron 70B is Q4_K_M, which balances quality and memory efficiency.

What speed will Nemotron 70B run at on RTX PRO 6000 Blackwell Server Edition 96GB?

On RTX PRO 6000 Blackwell Server Edition 96GB, Nemotron 70B achieves approximately 31.4 tokens per second decode speed with a time-to-first-token of 6162ms using Q4_K_M quantization.

Can RTX PRO 6000 Blackwell Server Edition 96GB run Nemotron 70B for coding?

For coding workloads, Nemotron 70B on RTX PRO 6000 Blackwell Server Edition 96GB receives a A grade with 31.4 tok/s and 131K context.

What context window can Nemotron 70B use on RTX PRO 6000 Blackwell Server Edition 96GB?

On RTX PRO 6000 Blackwell Server Edition 96GB, Nemotron 70B can safely use up to 131K tokens of context. The model's official context limit is 131K, but available memory constrains the safe maximum.

See all results for RTX PRO 6000 Blackwell Server Edition 96GBSee all hardware for Nemotron 70B
Embed this result▼

Paste this snippet into any page to show a live fit card.

<iframe src="https://willitrunai.com/embed/nemotron-70b-on-rtx-pro-6000-blackwell-server-96gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>

Preview: