Can you run GPT-OSS 20B on RTX 3090?

GPT-OSS 20B MXFP4 on the NVIDIA GeForce RTX 3090 — verdict, VRAM math and estimated speed.

Yes, it runs
Quick answer

Yes, the NVIDIA GeForce RTX 3090 runs GPT-OSS 20B. 13.8 GB weights at MXFP4 vs 21.6 GB usable VRAM; ~73 tok/s est..

$ollama run gpt-oss:20b
VERDICT
Comfortable
EST. SPEED
~73 tok/s
WEIGHTS
13.8 GB MXFP4

VRAM math and speed are ModelFit engine estimates, not measurements. Commands are registry-verified Ollama tags.

Cite this page: ModelFit, GPT-OSS 20B on RTX 3090, https://modelfit.io/can-i-run/gpt-oss-20b-on-rtx-3090/, updated August 2026, CC BY 4.0.

Last updated: August 16, 2026 · Editor: ModelFit Team

VRAM
24 GB (21.6 usable)
Model weights
13.8 GB MXFP4
Est. speed
~73 tok/s
First token
~0.4s

Memory math: weights + context vs budget

Weights take 13.8 GB. Context costs extra KV-cache on top — this is where long-context sessions break on cards that technically fit the weights.

ContextKV-cacheTotalFits
8k tokens2.0 GB15.8 GBFits
16k tokens4.0 GB17.8 GBFits
32k tokens8.0 GB21.8 GBOver
64k tokens16.0 GB29.8 GBOver
128k tokens32.0 GB45.8 GBOver

KV-cache figures assume an fp16 cache, the llama.cpp/Ollama default. Standard GQA models use a size-class estimate (8 KV heads x 128 head dim class); hybrid linear-attention models (Qwen3.5/3.6, Qwen3-Next) use the exact per-token cost from their published config, since only their sparse full-attention layers cache KV. A q8_0 KV cache roughly halves either figure. Estimates, not measurements.

GPT-OSS 20B on RTX 3090: FAQ

Can the NVIDIA GeForce RTX 3090 run GPT-OSS 20B?

Yes. GPT-OSS 20B (MXFP4) loads in about 13.8 GB and the RTX 3090 offers 21.6 GB of usable VRAM, leaving headroom for context. Expect at roughly 73 tokens/sec (est.).

How much VRAM does GPT-OSS 20B need?

About 13.8 GB for the weights at MXFP4, plus KV-cache for context: roughly 4.0 GB extra at 16k tokens. The RTX 3090 budget is 21.6 GB (24 GB x 90%).

What is the best quantization of GPT-OSS 20B for the RTX 3090?

Stick with the MXFP4 build at 13.8 GB — every heavier quant exceeds the 21.6 GB usable VRAM.

What GPU do I need to run GPT-OSS 20B comfortably?

The RTX 3090 already runs GPT-OSS 20B comfortably. Larger cards only buy you longer context or a heavier quant.