Can AMD Radeon PRO W7800 run DeepSeek R1 70B?
70B parameter LLM model on 32GB GDDR6 ECC
Barely — requires CPU/RAM offloading
~1-3 tok/s (offload)
SpeedVery slow — expect 1-3 tokens/sec
QualityQuality is fine but the speed makes it impractical for interactive use
AMD GPUs lack CUDA. While DeepSeek R1 70B can technically run via llama.cpp/GGUF, the setup is more complex and less optimized than on NVIDIA hardware.
VRAM Requirements
DeepSeek R1 70B is a 70B parameter model. At full precision (FP16), it requires 140GB of VRAM. Your AMD Radeon PRO W7800 only has 32GB — not enough even at maximum compression.
FP16 (Full Precision)140GB (need 108GB more)
Maximum quality, no quantization
Q8 (8-bit)70GB (need 38GB more)
Near-lossless, ~50% size reduction
Q4 (4-bit)40GB (need 8GB more)
Good quality, ~75% size reduction
Your GPU VRAM: 32GB GDDR6 ECC at 576 GB/s bandwidth
Recommended system RAM: 64GB DDR5 (2x GPU VRAM minimum for model overflow)
Recommended system RAM: 64GB DDR5 (2x GPU VRAM minimum for model overflow)
How to Set It Up
Step 1: Install Ollama
curl -fsSL https://ollama.com/install.sh | shOllama is the easiest way to run local LLMs. Works on Linux, macOS, and Windows.
Step 2: Download and run DeepSeek R1 70B
ollama run deepseek-r1:70b:q4_K_MThis downloads the model (~70GB). First run takes a few minutes.
Step 3: Verify GPU is being used
rocm-smiCheck that VRAM usage increases when the model loads. You should see ~40GB used.
AMD Radeon PRO W7800 Specs
VRAM32GB GDDR6 ECC
Memory Bandwidth576 GB/s
TDP260W
CUDA CoresN/A
Street Price~$2300
AI Rating5/10
Other GPUs That Run DeepSeek R1 70B
Other LLM Models on AMD Radeon PRO W7800
About DeepSeek R1 70B
Strong reasoning model. Same tier as Llama 70B for hardware requirements.
Category: LLM · Parameters: 70B · CUDA required: No (runs via llama.cpp/GGUF)