Skip to content

Kimi K2.6 on DGX Station GB300: VRAM, speed and fit

Kimi K2.6 at 1.6-bit runs on the DGX Station GB300 with 256K of context at about 200 tokens a second.

Text generation · Chat · Ollama / LM Studio

Runs comfortably · on DGX Station GB300 · 1.6-bit (IQ1_S) · Ollama / LM Studio · Chat

GPU memory
215 GB
of 252 GB
Context
256K
auto
Speed
200 tok/s
115 when full
First reply
0.6 s
2K prompt

Where the memory goes

Model
197 GB
Context
17.2 GB
Overhead
1.0 GB
OS
0.0 GB
Free
36.6 GB
In RAM
0.0 GB
Memory
215 GB of 252 GB
Context
256K tokens · auto
Speed
200 tok/s · 115 when full
First reply
0.6 s for a 2K prompt
Running cost
$23/mo at home · $574/mo on a cloud 8× A40

Validation: Validated

What Kimi K2.6 on DGX Station GB300 was checked against
CheckTargetResultStatus
Fits in GPU memory252 GB usable215 GB neededPass
Headroom5% free36.6 GB free (15%)Pass
Context for chat16K or more256KPass
Writing speed15 tok/s or more200 tok/sPass
First replyunder 3 s, 2K prompt0.6 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 K2.6
Parameters
1T, 32B active
Precision
1.6-bit (IQ1_S)
Context
256K, auto
Chats at once
1
Use
Chat
Runs in
Ollama / LM Studio
Hardware
DGX Station GB300
GPU can use
252 GB of 252 GB
Spill space
480 GB LPDDR5X on the Grace CPU

Running cost

At home
$23/mo
1040 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-K2.6-GGUF
vLLM
vllm serve moonshotai/Kimi-K2.6
MLX (Mac)
mlx_lm.chat --model mlx-community/Kimi-K2.6-mlx-DQ3_K_M-q8

Kimi K2.6 on similar machines

All machines: Kimi K2.6 VRAM requirements. Everything that runs here: what can the DGX Station GB300 run?

Other models that run on DGX Station GB300

Questions

Can Kimi K2.6 run on DGX Station GB300?

Kimi K2.6 at 1.6-bit runs on the DGX Station GB300 with 256K of context at about 200 tokens a second.

Report VR-08KDH9E, calculated Nov 22, 2026 from published specs, not benchmarked.