Can OLMo 2 32B run on NVIDIA B200 180GB?

YES — Runs Great

A79Great

○Estimated from fit model

OLMo 2 32B needs ~42.6 GB VRAM. NVIDIA B200 180GB has 180.0 GB. With Q4_K_M quantization, expect ~372 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) — 42.6 GB, 371.8 tok/s, Runs well

42.6 GB required180.0 GB available

24% VRAM used

Fit status

Runs well

Decode

371.8 tok/s

TTFT

521 ms

Safe context

Memory

42.6 GB / 180.0 GB

Memory breakdown

Weights19.5 GB

KV Cache3.9 GB

Runtime1.2 GB

Headroom18.0 GB

See how fast it feels

See how fast it feelsOLMo 2 32B on NVIDIA B200 180GB
1st promptCold start — includes initialization
>What is local AI inference?
Local AI inference means running an AI language model directly on your own hardware — your laptop, desktop, or server — instead of sending requests to a remote cloud API.

When you run inference locally the model weights are loaded into your GPU or unified memory. Each token you generate requires reading those weights from memory, so memory bandwidth is the main bottleneck for decode speed.

Key benefits of running locally:
 - Full privacy: your prompts never leave your machine
 - No per-token cost or rate limits
 - Works offline once the model is downloaded
 - Latency depends only on your hardware
2nd promptWarm — model ready, no init overhead
>How much VRAM do I need?
It depends on the model size and quantization level. A rough rule of thumb:

 Model size Q4 (4-bit) Q8 (8-bit) FP16
 7B params ~4.3 GB ~7.5 GB ~14 GB
 13B params ~7.9 GB ~13.9 GB ~26 GB
 70B params ~42.7 GB ~74.9 GB ~140 GB

Most people use 4-bit quantization (Q4_K_M) which gives 90-95% of full quality at a fraction of the memory. A 24 GB GPU can comfortably run most 7B-13B models.
Estimated: 371.8 tok/s decode · 521ms TTFT (warm) · 930 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	371.8 tok/s	350 ms	4K
Coding	A	Runs well	371.8 tok/s	521 ms	4K
Agentic Coding	A	Runs well	371.8 tok/s	757 ms	4K
Reasoning	A	Runs well	371.8 tok/s	615 ms	4K
RAG	A	Runs well	371.8 tok/s	947 ms	4K

Quantization options

How OLMo 2 32B (32B params) fits at each quantization level on NVIDIA B200 180GB (180.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	12.5 GB	Low	B70
Q3_K_S	3	15.7 GB	Low	B70
NVFP4	4	17.9 GB	Medium	B70
Q4_K_M	4	19.5 GB	Medium	B70
Q5_K_M	5	23.0 GB	High	A70
Q6_K	6	26.2 GB	High	A71
Q8_0	8	34.2 GB	Very High	A72
F16Best for your GPU	16	65.6 GB	Maximum	A75

Get started

Copy-paste commands to run OLMo 2 32B on your machine.

Run

lms load OLMo-2-0325-32B-Instruct && lms server start

Your hardware

More models your NVIDIA B200 180GB can run

Model	Params	Grade	Decode
👁 Mistral Devstral 2 123B Instruct	123B	S	97.4 tok/s
👁 Alibaba Qwen 3.5 122B A10B	122B	S	270.2 tok/s
👁 DeepSeek DeepSeek V4 Flash	284B	S	144.8 tok/s
👁 Alibaba Qwen 3.6 35B A3B	35B	S	854 tok/s
👁 Alibaba Qwen 3.5 35B A3B	35B	S	928.7 tok/s

Frequently asked questions

See all results for NVIDIA B200 180GB See all hardware for OLMo 2 32B

URL: https://willitrunai.com/can-run/olmo-2-32b-on-b200-180gb