text model · dots.llm · Windows
Can I run dots.llm1 on Nvidia GeForce RTX 3060 (12GB)?
No. dots.llm1 needs ~98.1 GB even at Q4_K_M, but Nvidia GeForce RTX 3060 (12GB) only has ~11 GB usable.
Needs ~98.1 GB even at Q4_K_M, but only ~11 GB is usable.
That figure is at a 4k context and moves about ±15% as context length changes.
The gap is about 87.1 GB: dots.llm1 needs roughly 98.1 GB at Q4_K_M and Nvidia GeForce RTX 3060 (12GB) leaves only about 11 GB usable for a model. The lightest tracked hardware that runs dots.llm1 is the Apple M3 Ultra (256GB) at 256 GB. See dots.llm1 on Apple M3 Ultra (256GB).
- Q4_K_M needed
- ~98.1 GB
- Usable on device
- ~11 GB
- Device memory
- 12 GB
Which quant fits
How to run it
On Windows use LM Studio (Best GUI on Windows, auto-detects CUDA/Vulkan backends.).
- Parameters
- 142B (MoE, 14B active)
- Q4_K_M size
- 94.4 GB
- Q8_0 size
- 151.9 GB
- Context
- 32k
- Memory
- 12 GB vram
- Usable for weights
- ~11 GB
- Power draw
- ~170 W
- Best runtime
- Ollama (CUDA) / llama.cpp CUDA
What you can run instead
Run dots.llm1 on other hardware
FAQ
Can Nvidia GeForce RTX 3060 (12GB) run dots.llm1?
No. dots.llm1 needs ~98.1 GB even at Q4_K_M, but Nvidia GeForce RTX 3060 (12GB) only has ~11 GB usable.
How much memory does dots.llm1 need?
Nvidia GeForce RTX 3060 (12GB) does not have enough memory. At Q4_K_M the weights are ~94.4 GB; with KV cache and runtime overhead, budget ~98.1 GB at a 4k context. It is a Mixture-of-Experts model (142B total / 14B active), so all experts must stay in memory; memory tracks total params, not active params.
What is the best tool to run dots.llm1 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/dots-llm1/nvidia-rtx-3060-12gb) 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.