Ornith 1.5 122B on 2× RTX 3090: VRAM, speed and fit
Ornith 1.5 122B at 4-bit needs 72.7 GB; the 2× RTX 3090 can use 48.0 GB. The smallest machine we checked that runs it is the RTX PRO 6000 Blackwell.
Text generation · Chat · Ollama / LM Studio
Won’t fit · on 2× RTX 3090 · 4-bit (Q4_K_M) · Ollama / LM Studio · Chat
- GPU memory
- 72.7 GB
- of 48.0 GB
- Context
- 8K
- auto
- Speed
- n/a
- First reply
- n/a
Where the memory goes
- Model
- 70.6 GB
- Context
- 339 MB
- Overhead
- 1.8 GB
- OS
- 0.0 GB
- Over by
- 24.7 GB
- Memory
- 72.7 GB of 48.0 GB
- Context
- 8K tokens · auto
- Speed
- Doesn’t run here
- Running cost
- Doesn’t run here · $122/mo on a cloud 4× RTX A4500
Validation: Not validated
| Check | Target | Result | Status |
|---|---|---|---|
| Fits in GPU memory | 48.0 GB usable | 72.7 GB needed | Fails |
| Headroom | 5% free | none | Fails |
| Context for chat | 16K or more | – | Not run |
| Writing speed | 15 tok/s or more | – | Not run |
| First reply | under 3 s, 2K prompt | – | Not run |
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 122B
- Parameters
- 125B, 12.7B active
- Precision
- 4-bit (Q4_K_M)
- Context
- 8K, 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
Worth trying
- 2-bit weights: Fits on the GPU, 8K context
- 4× RTX 3090: Fits across the cards, 256K context
- RTX PRO 6000 Blackwell: Runs it with 256K context
- M5 Max · 128 GB: Runs it with 256K context
Running cost
- At home
- n/a
- Doesn’t run on this machine.
- Renting instead
- $122/mo
- 4× RTX A4500 at $1.00/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 unsloth/Ornith-1.5-122B-GGUF- vLLM
vllm serve ornith-ai/Ornith-1.5-122B- Model card
- huggingface.co/ornith-ai/Ornith-1.5-122B
Ornith 1.5 122B on similar machines
- RTX 3090Too big
- RTX 4090Too big
- Radeon AI PRO R9700Too big
- RTX 5090Too big
- 2× RTX 4090Just misses
- RTX PRO 5000 Blackwell 48 GBRuns
- RTX 6000 AdaRuns
- L40SRuns
All machines: Ornith 1.5 122B VRAM requirements. Everything that runs here: what can the 2× RTX 3090 run?
Other models that run on 2× RTX 3090
Questions
Can Ornith 1.5 122B run on 2× RTX 3090?
Ornith 1.5 122B at 4-bit needs 72.7 GB; the 2× RTX 3090 can use 48.0 GB. The smallest machine we checked that runs it is the RTX PRO 6000 Blackwell.
Shown at the closest setup. Report VR-19HEBUO, calculated Nov 22, 2026 from published specs, not benchmarked.