Can DeepSeek R1 Distill 32B run on RTX 5090 32GB?

YES — Tight Fit

A78Great

○Estimated from fit model

DeepSeek R1 Distill 32B needs ~27.8 GB VRAM. RTX 5090 32GB has 32.0 GB. With Q4_K_M quantization, expect ~66 tok/s.

Runtime: OllamaCapacity: TightBandwidth: 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) — 27.8 GB, 66.4 tok/s, Tight fit

27.8 GB required32.0 GB available

87% VRAM used

Fit status

Tight fit

Decode

66.4 tok/s

TTFT

2914 ms

Safe context

33K

Memory

27.8 GB / 32.0 GB

Memory breakdown

Weights19.5 GB

KV Cache3.9 GB

Runtime1.2 GB

Headroom3.2 GB

See how fast it feels

See how fast it feelsDeepSeek R1 Distill 32B on RTX 5090 32GB
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: 66.4 tok/s decode · 2.9s TTFT (warm) · 166 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	A	Runs well	66.4 tok/s	1590 ms	33K
Coding	A	Tight fit	66.4 tok/s	2914 ms	33K
Agentic Coding	A	Runs with offload	66.4 tok/s	4239 ms	33K
Reasoning	A	Tight fit	66.4 tok/s	3444 ms	33K
RAG	A	Runs with offload	66.4 tok/s	5299 ms	33K

Quantization options

How DeepSeek R1 Distill 32B (32B params) fits at each quantization level on RTX 5090 32GB (32.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	12.5 GB	Low	A73
Q3_K_S	3	15.7 GB	Low	A75
NVFP4	4	17.9 GB	Medium	A75
Q4_K_M	4	19.5 GB	Medium	A74
Q5_K_MBest for your GPU	5	23.0 GB	High	A74
Q6_K	6	26.2 GB	High	F0
Q8_0	8	34.2 GB	Very High	F0
F16	16	65.6 GB	Maximum	F0

Get started

Copy-paste commands to run DeepSeek R1 Distill 32B on your machine.

Run

ollama run deepseek-r1:32b

Your hardware

More models your RTX 5090 32GB can run

Model	Params	Grade	Decode
👁 Alibaba Qwen 3.6 35B A3B	35B	S	128.2 tok/s
👁 Alibaba Qwen 3.5 35B A3B	35B	S	139.4 tok/s
👁 Moonshot AI Kimi Linear 48B A3B	48B	A	26.7 tok/s
👁 IBM Granite Code 34B	34B	A	62.7 tok/s
👁 Cohere Command R 35B	35B	A	61.2 tok/s

Frequently asked questions

See all results for RTX 5090 32GB See all hardware for DeepSeek R1 Distill 32B

URL: https://willitrunai.com/can-run/deepseek-r1-distill-32b-on-rtx-5090-32gb

⇱ DeepSeek R1 Distill 32B on RTX 5090 32GB? TIGHT FIT