Skip to content

DeepSeek V3.2 on M5 Ultra 512 GB: VRAM, speed and fit

DeepSeek V3.2 at 3-bit runs on the M5 Ultra 512 GB with 160K of context at about 32 tokens a second.

Text generation · Chat · Ollama / LM Studio

Runs comfortably · on M5 Ultra 512 GB · 3-bit (Q3_K_M) · Ollama / LM Studio · Chat

GPU memory
446 GB
of 512 GB
Context
160K
auto
Speed
32 tok/s
21 when full
First reply
7.2 s
2K prompt

Where the memory goes

Model
305 GB
Context
11.9 GB
Overhead
733 MB
OS
128 GB
Free
65.9 GB
Memory
446 GB of 512 GB
Context
160K tokens · auto
Speed
32 tok/s · 21 when full
First reply
7.2 s for a 2K prompt
Running cost
$5.06/mo at home · $574/mo on a cloud 8× A40

Validation: Not validated

What DeepSeek V3.2 on M5 Ultra 512 GB was checked against
CheckTargetResultStatus
Fits in GPU memory384 GB usable318 GB neededPass
Headroom5% free65.9 GB free (17%)Pass
Context for chat16K or more160KPass
Writing speed15 tok/s or more32 tok/sPass
First replyunder 3 s, 2K prompt7.2 sFails

Targets: a reply you can read along with, a first reply the use case tolerates, and 5% of memory left free. Calculated from published specs, not benchmarked.

The setup

Model
DeepSeek V3.2
Parameters
671B, 37B active
Precision
3-bit (Q3_K_M)
Context
160K, auto
Chats at once
1
Use
Chat
Runs in
Ollama / LM Studio
Hardware
M5 Ultra 512 GB
GPU can use
384 GB of 512 GB

Running cost

At home
$5.06/mo
231 W at the wall
Renting instead
$574/mo
8× A40 at $4.72/h

4 h a day, power at $0.18 per kWh, cloud at RunPod on-demand prices as of Nov 22, 2026.

How to run it

llama.cpp
llama-server -hf unsloth/DeepSeek-V3.2-GGUF
vLLM
vllm serve deepseek-ai/DeepSeek-V3.2
MLX (Mac)
mlx_lm.chat --model mlx-community/DeepSeek-V3.2-4bit

DeepSeek V3.2 on similar machines

  • M5 Max 128 GBToo big
  • M3 Ultra 96 GBToo big
  • M3 Ultra 256 GBRuns
  • M3 Ultra 512 GBRuns
  • Ryzen AI Max+ 395 64 GBToo big
  • Ryzen AI Max+ 395 128 GBToo big
  • RTX SparkJust misses
  • DGX SparkJust misses

All machines: DeepSeek V3.2 VRAM requirements. Everything that runs here: what can the M5 Ultra 512 GB run?

Other models that run on M5 Ultra 512 GB

Questions

Can DeepSeek V3.2 run on M5 Ultra 512 GB?

DeepSeek V3.2 at 3-bit runs on the M5 Ultra 512 GB with 160K of context at about 32 tokens a second.

Report VR-0RHD1VW, calculated Nov 22, 2026 from published specs, not benchmarked.