text model · MiniCPM · Windows
Can I run MiniCPM-V 4.6 on Nvidia GeForce RTX 4060 Ti (16GB)?
Yes. MiniCPM-V 4.6 runs on Nvidia GeForce RTX 4060 Ti (16GB) at Q4_K_M (~1.6 GB of ~15 GB usable).
Runs at Q4_K_M using ~1.6 GB of ~15 GB usable. You have room for FP16 for higher quality.
That figure is at a 4k context and moves about ±15% as context length changes. Nvidia GeForce RTX 4060 Ti (16GB) leaves ~13.4 GB of headroom, room to step up to FP16 for higher quality.
- Q4_K_M needed
- ~1.6 GB
- Usable on device
- ~15 GB
- Device memory
- 16 GB
- Best quant
- Q4_K_M
Which quant fits
Running cost · estimate
- Power draw
- ~165 W
- Electricity / 1M tokens
- ~$0.02
- Pays for itself after
- ~1,040M tok
At ~$0.15/kWh and the estimated ~353 tok/s, a million generated tokens costs about $0.02 in electricity. Versus a hosted API at ~$0.5 per million tokens, the ~$499 Nvidia GeForce RTX 4060 Ti (16GB) pays for itself after roughly 1,040 million tokens, so local hardware is mostly a fixed cost, not a per-token one. TDP is the peak draw, so this is an upper bound. Assumptions.
Run it
Pick your tool. All 3 load the same Q4_K_M weights.
ollama run minicpm-v4.6 llama-cli -hf openbmb/MiniCPM-V-4_6-gguf:Q4_K_M lms get openbmb/MiniCPM-V-4_6-gguf - Parameters
- 1.3B
- Q4_K_M size
- 0.53 GB
- Q8_0 size
- 0.81 GB
- Context
- 256k
- Ollama tag
- minicpm-v4.6
- Memory
- 16 GB vram
- Usable for weights
- ~15 GB
- Power draw
- ~165 W
- Best runtime
- Ollama (CUDA) / llama.cpp CUDA
You could also run
Run MiniCPM-V 4.6 on other hardware
FAQ
Can Nvidia GeForce RTX 4060 Ti (16GB) run MiniCPM-V 4.6?
Yes. MiniCPM-V 4.6 runs on Nvidia GeForce RTX 4060 Ti (16GB) at Q4_K_M (~1.6 GB of ~15 GB usable).
How much memory does MiniCPM-V 4.6 need?
Nvidia GeForce RTX 4060 Ti (16GB) has room to spare. At Q4_K_M the weights are ~0.53 GB; with KV cache and runtime overhead, budget ~1.6 GB at a 4k context.
What is the best tool to run MiniCPM-V 4.6 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/minicpm-v-4.6/nvidia-rtx-4060-ti-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.