How much VRAM does OLMo 2 13B need?

OLMo 2 13B (13B parameters) requires approximately 12.5 GB of memory with Q4_K_M quantization.

What is the best quantization for OLMo 2 13B?

The recommended quantization for OLMo 2 13B is Q4_K_M, which balances quality and memory efficiency.

Can it run?

Yes, RX 7600 XT 16GB can run OLMo 2 13B with a C grade (Runs well). Expected decode speed: 26.1 tok/s.

CUsable

Runs well

Using Q4_K_M in llama.cpp

Capabilities:

Fit status

Runs well

Decode

26.1 tok/s

TTFT

7404 ms

Safe context

21K

Memory

12.5 GB / 16.0 GB

Weights7.9 GB

KV Cache2.0 GB

Runtime0.9 GB

Headroom1.6 GB

Workload	Grade	Fit	Decode	TTFT	Context
Agentic Coding	C	Tight fit	21.1 tok/s	13369 ms	33K
Chat	C	Runs well	21.1 tok/s	5013 ms	11K
Coding	C	Runs well	26.1 tok/s	7404 ms	21K
RAG	C	Tight fit	21.1 tok/s	16711 ms	33K
Reasoning	C	Runs well	21.1 tok/s	10862 ms	21K

How OLMo 2 13B (13B params) fits at each quantization level on RX 7600 XT 16GB (16.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	5.1 GB	Low	D36
Q3_K_S	3	6.4 GB	Low	D37
NVFP4	4

HuggingFace

huggingface-cli download olmo-2-13b

Upgrade options

RX 7900 XT 20GBBudget pick

C60.5 tok/s decode

~$899 MSRP

RX 7900 XTX 24GBBest value

C87.2 tok/s decode

~$999 MSRP

RTX A4500 20GBBiggest leap