Skip to content

Kimi K3 on 8× H200 NVL: VRAM, speed and fit

Kimi K3 at 2-bit runs on the 8× H200 NVL with 1M of context at about 58 tokens a second.

Text generation · Chat · Ollama / LM Studio

Runs comfortably · on 8× H200 NVL · 2-bit (Q2_K) · Ollama / LM Studio · Chat

GPU memory
1,004 GB
of 1,128 GB
Context
1M
auto
Speed
58 tok/s
39 when full
First reply
0.9 s
2K prompt

Where the memory goes

Model
971 GB
Context
27.4 GB
Overhead
6.0 GB
OS
0.0 GB
Free
124 GB
Memory
1,004 GB of 1,128 GB
Context
1M tokens · auto
Speed
58 tok/s · 39 when full
First reply
0.9 s for a 2K prompt
Running cost
$65/mo at home · $2,325/mo on a cloud 8× MI300X

Validation: Validated

What Kimi K3 on 8× H200 NVL was checked against
CheckTargetResultStatus
Fits in GPU memory1,128 GB usable1,004 GB neededPass
Headroom5% free124 GB free (11%)Pass
Context for chat16K or more1MPass
Writing speed15 tok/s or more58 tok/sPass
First replyunder 3 s, 2K prompt0.9 sPass

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
2-bit (Q2_K)
Context
1M, auto
Chats at once
1
Use
Chat
Runs in
Ollama / LM Studio
Hardware
8× H200 NVL
GPU can use
1,128 GB of 1,128 GB

Running cost

At home
$65/mo
2960 W at the wall
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 8× H200 NVL run?

Other models that run on 8× H200 NVL

Questions

Can Kimi K3 run on 8× H200 NVL?

Kimi K3 at 2-bit runs on the 8× H200 NVL with 1M of context at about 58 tokens a second.

Report VR-1V4P0HF, calculated Nov 22, 2026 from published specs, not benchmarked.