Skip to content
localmodel.run

text model · DeepSeek-R1 · macOS

Can I run DeepSeek R1 on Apple M3 Pro (18GB)?

Compatibility verdict VRAM threshold engine
No, not enough memorywould not load

No. DeepSeek R1 needs ~383.7 GB even at Q4_K_M, but Apple M3 Pro (18GB) only has ~12 GB usable.

Needs ~383.7 GB Device usable ~12 GB

Needs ~383.7 GB even at Q4_K_M, but only ~12 GB is usable.

Q4_K_M needed
~383.7 GB
Usable on device
~12 GB
Device memory
18 GB
Model DeepSeek-R1
Parameters
671B (MoE, 37B active)
Q4_K_M size
376.66 GB
Context
128k
Ollama tag
deepseek-r1:671b
Full DeepSeek R1 requirements →
Device macOS
Memory
18 GB unified
Usable for weights
~12 GB
Best runtime
Ollama (llama.cpp Metal backend) / MLX
Best models for Apple M3 Pro (18GB) →

What you can run instead

FAQ

Can Apple M3 Pro (18GB) run DeepSeek R1?

No. DeepSeek R1 needs ~383.7 GB even at Q4_K_M, but Apple M3 Pro (18GB) only has ~12 GB usable.

How much memory does DeepSeek R1 need?

Apple M3 Pro (18GB) does not have enough memory. At Q4_K_M the weights are ~376.66 GB; with KV cache and runtime overhead, budget ~383.7 GB at a 4k context. It is a Mixture-of-Experts model (671B total / 37B active), so all experts must stay in memory; memory tracks total params, not active params.

What is the best tool to run DeepSeek R1 on macOS?

LM Studio for a simple setup; mlx-lm for the most speed. vLLM is NOT a Mac tool, it is a CUDA/Linux serving engine. Unified memory is not a fixed VRAM slice; ~70% is usable for weights.

Sources

Memory figures are estimates. See methodology.