text model · Ornith · Windows
Can I run Ornith 1.0 35B on Nvidia GeForce RTX 4080 (16GB)?
No. Ornith 1.0 35B needs ~23.2 GB even at Q4_K_M, but Nvidia GeForce RTX 4080 (16GB) only has ~15 GB usable.
Needs ~23.2 GB even at Q4_K_M, but only ~15 GB is usable.
That figure is at a 4k context and moves about ±15% as context length changes.
The gap is about 8.2 GB: Ornith 1.0 35B needs roughly 23.2 GB at Q4_K_M and Nvidia GeForce RTX 4080 (16GB) leaves only about 15 GB usable for a model. The lightest tracked hardware that runs Ornith 1.0 35B is the Nvidia GeForce RTX 5090 (32GB) at 32 GB. See Ornith 1.0 35B on Nvidia GeForce RTX 5090 (32GB).
- Q4_K_M needed
- ~23.2 GB
- Usable on device
- ~15 GB
- Device memory
- 16 GB
Which quant fits
- Parameters
- 35B (MoE, 3B active)
- Q4_K_M size
- 21 GB
- Q8_0 size
- 37 GB
- Context
- 256k
- Ollama tag
- ornith:35b
- Memory
- 16 GB vram
- Usable for weights
- ~15 GB
- Power draw
- ~320 W
- Best runtime
- vLLM (Linux) / Ollama (CUDA)
What you can run instead
Run Ornith 1.0 35B on other hardware
FAQ
Can Nvidia GeForce RTX 4080 (16GB) run Ornith 1.0 35B?
No. Ornith 1.0 35B needs ~23.2 GB even at Q4_K_M, but Nvidia GeForce RTX 4080 (16GB) only has ~15 GB usable.
How much memory does Ornith 1.0 35B need?
Nvidia GeForce RTX 4080 (16GB) does not have enough memory. At Q4_K_M the weights are ~21 GB; with KV cache and runtime overhead, budget ~23.2 GB at a 4k context. It is a Mixture-of-Experts model (35B total / 3B active), so all experts must stay in memory; memory tracks total params, not active params.
What is the best tool to run Ornith 1.0 35B on Windows?
LM Studio for a simple setup; Ollama (CUDA) for the most speed. AMD GPUs run via Vulkan/ROCm at roughly half CUDA throughput. NVIDIA is the smooth path on Windows.
Embed this
A live badge for your model card or README, updated as the data is. [](https://localmodel.run/can-i-run/ornith-1.0-35b/nvidia-rtx-4080-16gb) Sources
Weights are measured from GGUF files; KV cache and overhead are computed, so totals can vary ~15% with context and runtime. Any tok/s is a bandwidth estimate. See methodology.