Skip to content

Ornith 1.5 9B on RTX 3060 12 GB: VRAM, speed and fit

Ornith 1.5 9B at 8-bit runs on the RTX 3060 12 GB with 20K of context at about 27 tokens a second.

Text generation · Chat · Ollama / LM Studio

Runs comfortably · on RTX 3060 12 GB · 8-bit (Q8_0) · Ollama / LM Studio · Chat

GPU memory
11.3 GB
of 12.0 GB
Context
20K
auto
Speed
27 tok/s
Fast
First reply
1.3 s
2K prompt

Where the memory goes

Model
9.6 GB
Context
689 MB
Overhead
1.0 GB
OS
0.0 GB
Free
744 MB
Memory
11.3 GB of 12.0 GB
Context
20K tokens · auto
Speed
27 tok/s · fast
First reply
1.3 s for a 2K prompt
Running cost
$3.98/mo at home · $29/mo on a cloud RTX 2000 Ada

Validation: Validated

What Ornith 1.5 9B on RTX 3060 12 GB was checked against
CheckTargetResultStatus
Fits in GPU memory12.0 GB usable11.3 GB neededPass
Headroom5% free744 MB free (6%)Pass
Context for chat16K or more20KPass
Writing speed15 tok/s or more27 tok/sPass
First replyunder 3 s, 2K prompt1.3 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
Ornith 1.5 9B
Parameters
9.7B
Precision
8-bit (Q8_0)
Context
20K, 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 44K 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

llama.cpp
llama-server -hf OBLITERATUS/Ornith-1.5-9B-OBLITERATED
vLLM
vllm serve ornith-ai/Ornith-1.5-9B

Ornith 1.5 9B on similar machines

All machines: Ornith 1.5 9B 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 Ornith 1.5 9B run on RTX 3060 12 GB?

Ornith 1.5 9B at 8-bit runs on the RTX 3060 12 GB with 20K of context at about 27 tokens a second.

Report VR-1HT1S0I, calculated Nov 22, 2026 from published specs, not benchmarked.