Can DeepSeek R1 Distill 14B run on NVIDIA B200 180GB?

YES — Runs Great

A70Great

Estimated from fit model

DeepSeek R1 Distill 14B needs ~30.7 GB VRAM. NVIDIA B200 180GB has 180.0 GB. With Q4_K_M quantization, expect ~196 tok/s.

Runtime: OllamaCapacity: RoomyBandwidth: HighStack: BasicBottleneck: Balanced

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) — 30.7 GB, 196.0 tok/s, Runs well

30.7 GB required180.0 GB available

17% VRAM used

Fit status

Runs well

Decode

196.0 tok/s

TTFT

988 ms

Safe context

33K

Memory

30.7 GB / 180.0 GB

Memory breakdown

Weights8.5 GB

KV Cache2.9 GB

Runtime1.2 GB

Headroom18.0 GB

See how fast it feels

See how fast it feelsDeepSeek R1 Distill 14B on NVIDIA B200 180GB
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: 196.0 tok/s decode · 988ms TTFT (warm) · 490 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

Workload	Grade	Fit	Decode	TTFT	Context
Chat	B	Runs well	196.0 tok/s	539 ms	33K
Coding	A	Runs well	196.0 tok/s	988 ms	33K
Agentic Coding	A	Runs well	196.0 tok/s	1437 ms	33K
Reasoning	A	Runs well	196.0 tok/s	1167 ms	33K
RAG	A	Runs well	196.0 tok/s	1796 ms	33K

Quantization options

How DeepSeek R1 Distill 14B (14B params) fits at each quantization level on NVIDIA B200 180GB (180.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	5.5 GB	Low	B62
Q3_K_S	3	6.9 GB	Low	B62
NVFP4	4	7.8 GB	Medium	B62
Q4_K_M	4	8.5 GB	Medium	B62
Q5_K_M	5	10.1 GB	High	B62
Q6_K	6	11.5 GB	High	B62
Q8_0	8	15.0 GB	Very High	B62
F16Best for your GPU	16	28.7 GB	Maximum	B63

Get started

Copy-paste commands to run DeepSeek R1 Distill 14B on your machine.

Run

ollama run deepseek-r1

Your hardware

More models your NVIDIA B200 180GB can run

Model	Params	Grade	Decode
Devstral 2 123B Instruct	123B	S	97.4 tok/s
Qwen3-Coder 30B A3B Instruct	30.5B	S	1016.1 tok/s
Qwen 3.5 27B	27B	S	378 tok/s
Qwen 3.6 27B	27B	S	378 tok/s
Qwen 3.5 122B A10B	122B	S	270.2 tok/s

Frequently asked questions

Can NVIDIA B200 180GB run DeepSeek R1 Distill 14B?

Yes, NVIDIA B200 180GB can run DeepSeek R1 Distill 14B with a A grade (Runs well). Expected decode speed: 196.0 tok/s.

How much VRAM does DeepSeek R1 Distill 14B need?

DeepSeek R1 Distill 14B (14B parameters) requires approximately 30.7 GB of memory with Q4_K_M quantization.

What is the best quantization for DeepSeek R1 Distill 14B?

The recommended quantization for DeepSeek R1 Distill 14B is Q4_K_M, which balances quality and memory efficiency.

What speed will DeepSeek R1 Distill 14B run at on NVIDIA B200 180GB?

On NVIDIA B200 180GB, DeepSeek R1 Distill 14B achieves approximately 196.0 tokens per second decode speed with a time-to-first-token of 988ms using Q4_K_M quantization.

Can NVIDIA B200 180GB run DeepSeek R1 Distill 14B for coding?

For coding workloads, DeepSeek R1 Distill 14B on NVIDIA B200 180GB receives a A grade with 196.0 tok/s and 33K context.

What context window can DeepSeek R1 Distill 14B use on NVIDIA B200 180GB?

On NVIDIA B200 180GB, DeepSeek R1 Distill 14B can safely use up to 33K tokens of context. The model's official context limit is 33K, but available memory constrains the safe maximum.

See all results for NVIDIA B200 180GB See all hardware for DeepSeek R1 Distill 14B

Embed this result▼

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

<iframe src="https://willitrunai.com/embed/deepseek-r1-distill-14b-on-b200-180gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>

Preview: