Skip to content

gpt-oss 20B on RTX 3060 12 GB: VRAM, speed and fit

gpt-oss 20B at 3-bit runs on the RTX 3060 12 GB with 40K of context at about 119 tokens a second.

Text generation · Chat · Ollama / LM Studio

Runs comfortably · on RTX 3060 12 GB · 3-bit (Q3_K_M) · Ollama / LM Studio · Chat

GPU memory
11.4 GB
of 12.0 GB
Context
40K
auto
Speed
119 tok/s
80 when full
First reply
1.4 s
2K prompt

Where the memory goes

Model
9.5 GB
Context
963 MB
Overhead
944 MB
OS
0.0 GB
Free
635 MB
Memory
11.4 GB of 12.0 GB
Context
40K tokens · auto
Speed
119 tok/s · 80 when full
First reply
1.4 s for a 2K prompt
Running cost
$3.98/mo at home · $29/mo on a cloud RTX 2000 Ada

Validation: Validated

What gpt-oss 20B on RTX 3060 12 GB was checked against
CheckTargetResultStatus
Fits in GPU memory12.0 GB usable11.4 GB neededPass
Headroom5% free635 MB free (5%)Pass
Context for chat16K or more40KPass
Writing speed15 tok/s or more119 tok/sPass
First replyunder 3 s, 2K prompt1.4 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 20B
Parameters
20.9B, 3.6B active
Precision
3-bit (Q3_K_M)
Context
40K, auto
Chats at once
1
Use
Chat
Runs in
Ollama / LM Studio
Hardware
RTX 3060 12 GB
GPU can use
12.0 GB of 12.0 GB

Worth trying

  • 8-bit cache: Room for 72K context

Running cost

At home
$3.98/mo
182 W at the wall
Renting instead
$29/mo
RTX 2000 Ada at $0.24/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:20b
llama.cpp
llama-server -hf unsloth/gpt-oss-20b-GGUF
vLLM
vllm serve openai/gpt-oss-20b
MLX (Mac)
mlx_lm.chat --model mlx-community/gpt-oss-20b-MXFP4-Q4

gpt-oss 20B on similar machines

  • RTX 4060Too big
  • RTX 5060Too big
  • RTX 3070Too big
  • RTX 3080 10 GBJust misses
  • Arc B580Runs
  • RTX 4070Runs
  • RTX 4070 SuperRuns
  • RTX 5070Runs

All machines: gpt-oss 20B VRAM requirements. Everything that runs here: what can the RTX 3060 12 GB run?

Other models that run on RTX 3060 12 GB

Questions

Can gpt-oss 20B run on RTX 3060 12 GB?

gpt-oss 20B at 3-bit runs on the RTX 3060 12 GB with 40K of context at about 119 tokens a second.

Report VR-08QCW96, calculated Nov 22, 2026 from published specs, not benchmarked.