Skip to content

Kimi K3 on 4× H200 NVL: VRAM, speed and fit

Kimi K3 at INT4 needs 1,457 GB; the 4× H200 NVL can use 564 GB.

Text generation · Chat · Ollama / LM Studio

Won’t fit · on 4× H200 NVL · INT4 · Ollama / LM Studio · Chat

GPU memory
1,457 GB
of 564 GB
Context
8K
auto
Speed
n/a
First reply
n/a

Where the memory goes

Model
1,454 GB
Context
645 MB
Overhead
3.1 GB
OS
0.0 GB
Over by
893 GB
Memory
1,457 GB of 564 GB
Context
8K tokens · auto
Speed
Doesn’t run here
Running cost
Doesn’t run here · $2,325/mo on a cloud 8× MI300X

Validation: Not validated

What Kimi K3 on 4× H200 NVL was checked against
CheckTargetResultStatus
Fits in GPU memory564 GB usable1,457 GB neededFails
Headroom5% freenoneFails
Context for chat16K or more–Not run
Writing speed15 tok/s or more–Not run
First replyunder 3 s, 2K prompt–Not run

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 K3
Parameters
2.8T, 104B active
Precision
INT4
Context
8K, auto
Chats at once
1
Use
Chat
Runs in
Ollama / LM Studio
Hardware
4× H200 NVL
GPU can use
564 GB of 564 GB

Worth trying

  • 1.6-bit weights: Fits on the GPU, 8K context

Running cost

At home
n/a
Doesn’t run on this machine.
Renting instead
$2,325/mo
8× MI300X at $19/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/Kimi-K3-GGUF
vLLM
vllm serve moonshotai/Kimi-K3

Kimi K3 on similar machines

All machines: Kimi K3 VRAM requirements. Everything that runs here: what can the 4× H200 NVL run?

Other models that run on 4× H200 NVL

Questions

Can Kimi K3 run on 4× H200 NVL?

Kimi K3 at INT4 needs 1,457 GB; the 4× H200 NVL can use 564 GB.

Shown at the closest setup. Report VR-0TQSI5V, calculated Nov 22, 2026 from published specs, not benchmarked.