VOOZH about

URL: https://willitrunai.com/can-run/deepseek-r1-distill-14b-on-quadro-rtx-8000-48gb

⇱ DeepSeek R1 Distill 14B on Quadro RTX 8000 48GB? YES

Can DeepSeek R1 Distill 14B run on Quadro RTX 8000 48GB?

YES — Runs Great

A73Great
○Estimated from fit model

DeepSeek R1 Distill 14B needs ~17.5 GB VRAM. Quadro RTX 8000 48GB has 48.0 GB. With Q4_K_M quantization, expect ~59 tok/s.

Runtime: OllamaCapacity: RoomyBandwidth: MediumStack: BasicBottleneck: 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) — 17.5 GB, 58.6 tok/s, Runs well
17.5 GB required48.0 GB available
36% VRAM used

Fit status

Runs well

Decode

58.6 tok/s

TTFT

3302 ms

Safe context

33K

Memory

17.5 GB / 48.0 GB

Memory breakdown

Weights8.5 GB
KV Cache2.9 GB
Runtime1.2 GB
Headroom4.8 GB

See how fast it feels

See how fast it feelsDeepSeek R1 Distill 14B on Quadro RTX 8000 48GB
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: 58.6 tok/s decode · 3.3s TTFT (warm) · 147 tok/s prefill

What limits this setup

This setup is broadly balanced for this model.

Older PCIe generation

PCIe 3.0 is workable, but it compounds the penalty when you offload heavily or try to scale across multiple cards.

Best improvement path

Performance by workload

WorkloadGradeFitDecodeTTFTContext
ChatARuns well58.6 tok/s1801 ms33K
CodingARuns well58.6 tok/s3302 ms33K
Agentic CodingARuns well58.6 tok/s4802 ms33K
ReasoningARuns well58.6 tok/s3902 ms33K
RAGARuns well58.6 tok/s6003 ms33K

Quantization options

How DeepSeek R1 Distill 14B (14B params) fits at each quantization level on Quadro RTX 8000 48GB (48.0 GB usable).

QuantBitsVRAMQualityFit
Q2_K
2
5.5 GB
LowB66
Q3_K_S
3
6.9 GB
LowB67
NVFP4
4
7.8 GB
MediumB67
Q4_K_M
4
8.5 GB
MediumB67
Q5_K_M
5
10.1 GB
HighB67
Q6_K
6
11.5 GB
HighB68
Q8_0
8
15.0 GB
Very HighB69
F16Best for your GPU
16
28.7 GB
MaximumA73

Get started

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

Run

ollama run deepseek-r1

Your hardware

More models your Quadro RTX 8000 48GB can run

ModelParamsGradeDecodeCapabilities
👁 Alibaba
Qwen3-Coder 30B A3B Instruct		30.5BS70.1 tok/s
👁 Alibaba
Qwen 3.5 27B		27BS30.4 tok/s
👁 Alibaba
Qwen 3.6 27B		27BS30.5 tok/s
👁 Alibaba
Qwen 3.6 35B A3B		35BS58.9 tok/s
👁 Alibaba
Qwen3-VL 30B A3B Instruct		30BS72.5 tok/s

Frequently asked questions

See all results for Quadro RTX 8000 48GBSee all hardware for DeepSeek R1 Distill 14B