How much VRAM does GPT-OSS 20B need?

GPT-OSS 20B (21B parameters) requires approximately 18.3 GB of memory with Q4_K_M quantization.

What is the best quantization for GPT-OSS 20B?

The recommended quantization for GPT-OSS 20B is Q4_K_M, which balances quality and memory efficiency.

Can it run?

Yes, MacBook Pro M4 32GB can run GPT-OSS 20B with a C grade (Runs well). Expected decode speed: 13.9 tok/s.

CUsable

Runs well

Using Q4_K_M in Ollama

Capabilities:

Fit status

Runs well

Decode

13.9 tok/s

TTFT

13899 ms

Safe context

20K

Memory

18.3 GB / 23.0 GB

Weights12.8 GB

KV Cache0.8 GB

Runtime1.2 GB

Headroom3.5 GB

Workload	Grade	Fit	Decode	TTFT	Context
Agentic Coding	C	Runs well	13.9 tok/s	20217 ms	40K
Chat	C	Runs well	13.9 tok/s	7581 ms	10K
Coding	C	Runs well	13.9 tok/s	13899 ms	20K
RAG	C	Runs well	13.9 tok/s	25271 ms	40K
Reasoning	C	Runs well	13.9 tok/s	16426 ms	20K

How GPT-OSS 20B (21B params) fits at each quantization level on MacBook Pro M4 32GB (23.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	8.2 GB	Low	D37
Q3_K_S	3	10.3 GB	Low	D39
NVFP4	4

Ollama

ollama run gpt-oss-20b

HuggingFace

huggingface-cli download gpt-oss-20b

Upgrade options

RX 7900 XTX 24GBBudget pick

B123.4 tok/s decode

~$999 MSRP

RTX 3090 24GBBest value

B117 tok/s decode

~$1,499 MSRP

MacBook Pro M4 Max 36GBApple upgrade