text model · DeepSeek-R1-Distill · Windows
Can I run DeepSeek-R1-Distill-Qwen 14B on Nvidia GeForce RTX 4070 (12GB)?
Yes. DeepSeek-R1-Distill-Qwen 14B runs on Nvidia GeForce RTX 4070 (12GB) at Q4_K_M (~10.7 GB of ~11 GB usable).
Fits at Q4_K_M (~10.7 GB of ~11 GB usable) but with little headroom, close other apps.
- Q4_K_M needed
- ~10.7 GB
- Usable on device
- ~11 GB
- Device memory
- 12 GB
- Best quant
- Q4_K_M
Run it
Pick your tool. All three load the same Q4_K_M weights.
ollama run deepseek-r1:14b llama-cli -hf bartowski/DeepSeek-R1-Distill-Qwen-14B-GGUF:Q4_K_M lms get bartowski/DeepSeek-R1-Distill-Qwen-14B-GGUF AMD GPUs run via Vulkan/ROCm at roughly half CUDA throughput. NVIDIA is the smooth path on Windows.
- Parameters
- 14B
- Q4_K_M size
- 8.99 GB
- Q8_0 size
- 15.7 GB
- Context
- 128k
- Ollama tag
- deepseek-r1:14b
- Memory
- 12 GB vram
- Usable for weights
- ~11 GB
- Best runtime
- Ollama (CUDA) / vLLM (Linux)
You could also run
Run DeepSeek-R1-Distill-Qwen 14B on other hardware
FAQ
Can Nvidia GeForce RTX 4070 (12GB) run DeepSeek-R1-Distill-Qwen 14B?
Yes. DeepSeek-R1-Distill-Qwen 14B runs on Nvidia GeForce RTX 4070 (12GB) at Q4_K_M (~10.7 GB of ~11 GB usable).
How much memory does DeepSeek-R1-Distill-Qwen 14B need?
It is a tight fit on Nvidia GeForce RTX 4070 (12GB). At Q4_K_M the weights are ~8.99 GB; with KV cache and runtime overhead, budget ~10.7 GB at a 4k context.
What is the best tool to run DeepSeek-R1-Distill-Qwen 14B 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.
Sources
Memory figures are estimates. See methodology.