Skip to content

gpt-oss 120B on 2× RTX 3090: VRAM, speed and fit

gpt-oss 120B at 2-bit runs on the 2× RTX 3090 with 88K of context at about 197 tokens a second.

Text generation · Chat · Ollama / LM Studio

Runs comfortably · on 2× RTX 3090 · 2-bit (Q2_K) · Ollama / LM Studio · Chat

GPU memory
45.5 GB
of 48.0 GB
Context
88K
auto
Speed
197 tok/s
98 when full
First reply
0.5 s
2K prompt

Where the memory goes

Model
40.8 GB
Context
3.1 GB
Overhead
1.6 GB
OS
0.0 GB
Free
2.5 GB
Memory
45.5 GB of 48.0 GB
Context
88K tokens · auto
Speed
197 tok/s · 98 when full
First reply
0.5 s for a 2K prompt
Running cost
$11/mo at home · $66/mo on a cloud 2× RTX A5000

Validation: Validated

What gpt-oss 120B on 2× RTX 3090 was checked against
CheckTargetResultStatus
Fits in GPU memory48.0 GB usable45.5 GB neededPass
Headroom5% free2.5 GB free (5%)Pass
Context for chat16K or more88KPass
Writing speed15 tok/s or more197 tok/sPass
First replyunder 3 s, 2K prompt0.5 sPass

Targets: a reply you can read along with, a first reply the use case tolerates, and 5% of memory left free. Calculated from published specs, not benchmarked.

The setup

Model
gpt-oss 120B
Parameters
117B, 5.1B active
Precision
2-bit (Q2_K)
Context
88K, auto
Chats at once
1
Use
Chat
Runs in
Ollama / LM Studio
Hardware
2× RTX 3090
GPU can use
48.0 GB of 48.0 GB

Running cost

At home
$11/mo
500 W at the wall
Renting instead
$66/mo
2× RTX A5000 at $0.54/h

4 h a day, power at $0.18 per kWh, cloud at RunPod on-demand prices as of Nov 21, 2026.

How to run it

Ollama
ollama run gpt-oss:120b
llama.cpp
llama-server -hf unsloth/gpt-oss-120b-GGUF
vLLM
vllm serve openai/gpt-oss-120b
MLX (Mac)
mlx_lm.chat --model mlx-community/gpt-oss-120b-MXFP4-Q4

gpt-oss 120B on similar machines

  • RTX 3090Too big
  • RTX 4090Too big
  • Radeon AI PRO R9700Too big
  • RTX 5090Too big
  • 2× RTX 4090Runs
  • RTX PRO 5000 Blackwell 48 GBRuns
  • RTX 6000 AdaRuns
  • L40SRuns

All machines: gpt-oss 120B VRAM requirements. Everything that runs here: what can the 2× RTX 3090 run?

Other models that run on 2× RTX 3090

Questions

Can gpt-oss 120B run on 2× RTX 3090?

gpt-oss 120B at 2-bit runs on the 2× RTX 3090 with 88K of context at about 197 tokens a second.

Report VR-0Q2EOB7, calculated Nov 22, 2026 from published specs, not benchmarked.