Skip to content

Kimi K2 Instruct on M5 Ultra 512 GB: VRAM, speed and fit

Kimi K2 Instruct at 2-bit runs on the M5 Ultra 512 GB with 80K 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
493 GB
of 512 GB
Context
80K
auto
Speed
35 tok/s
28 when full
First reply
8.0 s
2K prompt

Where the memory goes

Model
358 GB
Context
5.4 GB
Overhead
800 MB
OS
128 GB
Free
19.4 GB
Memory
493 GB of 512 GB
Context
80K tokens · auto
Speed
35 tok/s · 28 when full
First reply
8.0 s for a 2K prompt
Running cost
$5.06/mo at home · $574/mo on a cloud 8× A40

Validation: Not validated

What Kimi K2 Instruct on M5 Ultra 512 GB was checked against
CheckTargetResultStatus
Fits in GPU memory384 GB usable365 GB neededPass
Headroom5% free19.4 GB free (5%)Pass
Context for chat16K or more80KPass
Writing speed15 tok/s or more35 tok/sPass
First replyunder 3 s, 2K prompt8.0 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
Kimi K2 Instruct
Parameters
1T, 41.5B active
Precision
2-bit (Q2_K)
Context
80K, 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/Kimi-K2-Instruct-GGUF
vLLM
vllm serve moonshotai/Kimi-K2-Instruct
MLX (Mac)
mlx_lm.chat --model mlx-community/Kimi-K2-Instruct-4bit

Kimi K2 Instruct on similar machines

  • M5 Max 128 GBToo big
  • M3 Ultra 96 GBToo big
  • M3 Ultra 256 GBJust misses
  • 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: Kimi K2 Instruct 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 Kimi K2 Instruct run on M5 Ultra 512 GB?

Kimi K2 Instruct at 2-bit runs on the M5 Ultra 512 GB with 80K of context at about 35 tokens a second.

Report VR-1U910V4, calculated Nov 22, 2026 from published specs, not benchmarked.