Skip to content

Inkling on M5 Ultra 512 GB: VRAM, speed and fit

Inkling at 2-bit runs on the M5 Ultra 512 GB with 4K of context at about 35 tokens a second.

Text generation · Chat · Ollama / LM Studio

Runs comfortably · on M5 Ultra 512 GB · 2-bit (Q2_K) · Ollama / LM Studio · Chat

GPU memory
462 GB
of 512 GB
Context
4K
auto
Speed
35 tok/s
Fast
First reply
7.9 s
2K prompt

Where the memory goes

Model
333 GB
Context
1.0 GB
Overhead
841 MB
OS
128 GB
Free
49.5 GB
Memory
462 GB of 512 GB
Context
4K tokens · auto
Speed
35 tok/s · fast
First reply
7.9 s for a 2K prompt
Running cost
$5.06/mo at home · $574/mo on a cloud 8× A40

Validation: Not validated

What Inkling on M5 Ultra 512 GB was checked against
CheckTargetResultStatus
Fits in GPU memory384 GB usable334 GB neededPass
Headroom5% free49.5 GB free (13%)Pass
Context for chat4K or more4KPass
Writing speed15 tok/s or more35 tok/sPass
First replyunder 3 s, 2K prompt7.9 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
Inkling
Parameters
952B, 40.9B active
Precision
2-bit (Q2_K)
Context
4K, 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 21, 2026.

How to run it

llama.cpp
llama-server -hf unsloth/inkling-GGUF
vLLM
vllm serve thinkingmachines/Inkling

Inkling 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 SparkToo big
  • DGX SparkToo big

All machines: Inkling 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 Inkling run on M5 Ultra 512 GB?

Inkling at 2-bit runs on the M5 Ultra 512 GB with 4K of context at about 35 tokens a second.

Report VR-0VHRR5L, calculated Nov 22, 2026 from published specs, not benchmarked.