Skip to content

Ornith 1.5 397B on 2× RTX PRO 6000 Blackwell: VRAM, speed and fit

Ornith 1.5 397B at 2-bit runs on the 2× RTX PRO 6000 Blackwell with 256K of context at about 91 tokens a second.

Text generation · Chat · Ollama / LM Studio

Runs comfortably · on 2× RTX PRO 6000 Blackwell · 2-bit (Q2_K) · Ollama / LM Studio · Chat

GPU memory
150 GB
of 192 GB
Context
256K
auto
Speed
91 tok/s
57 when full
First reply
0.7 s
2K prompt

Where the memory goes

Model
141 GB
Context
7.7 GB
Overhead
1.8 GB
OS
0.0 GB
Free
41.6 GB
Memory
150 GB of 192 GB
Context
256K tokens · auto
Speed
91 tok/s · 57 when full
First reply
0.7 s for a 2K prompt
Running cost
$18/mo at home · $287/mo on a cloud 4× A40

Validation: Validated

What Ornith 1.5 397B on 2× RTX PRO 6000 Blackwell was checked against
CheckTargetResultStatus
Fits in GPU memory192 GB usable150 GB neededPass
Headroom5% free41.6 GB free (22%)Pass
Context for chat16K or more256KPass
Writing speed15 tok/s or more91 tok/sPass
First replyunder 3 s, 2K prompt0.7 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 397B
Parameters
403B, 24.4B active
Precision
2-bit (Q2_K)
Context
256K, auto
Chats at once
1
Use
Chat
Runs in
Ollama / LM Studio
Hardware
2× RTX PRO 6000 Blackwell
GPU can use
192 GB of 192 GB

Running cost

At home
$18/mo
800 W at the wall
Renting instead
$287/mo
4× A40 at $2.36/h

4 h a day, power at $0.18 per kWh, cloud at RunPod on-demand prices as of Nov 22, 2026.

How to run it

llama.cpp
llama-server -hf zephel01/Ornith-1.5-397B-IQ2_XXS-32G128G-GGUF
vLLM
vllm serve ornith-ai/Ornith-1.5-397B

Ornith 1.5 397B on similar machines

All machines: Ornith 1.5 397B VRAM requirements. Everything that runs here: what can the 2× RTX PRO 6000 Blackwell run?

Other models that run on 2× RTX PRO 6000 Blackwell

Questions

Can Ornith 1.5 397B run on 2× RTX PRO 6000 Blackwell?

Ornith 1.5 397B at 2-bit runs on the 2× RTX PRO 6000 Blackwell with 256K of context at about 91 tokens a second.

Report VR-0EHJH7Z, calculated Nov 22, 2026 from published specs, not benchmarked.