Skip to content

Kimi K2.6 on 4× RTX PRO 6000 Blackwell: VRAM, speed and fit

Kimi K2.6 at 2-bit runs on the 4× RTX PRO 6000 Blackwell with 44K of context at about 76 tokens a second.

Text generation · Chat · Ollama / LM Studio

Runs comfortably · on 4× RTX PRO 6000 Blackwell · 2-bit (Q2_K) · Ollama / LM Studio · Chat

GPU memory
365 GB
of 384 GB
Context
44K
auto
Speed
76 tok/s
63 when full
First reply
0.5 s
2K prompt

Where the memory goes

Model
359 GB
Context
2.9 GB
Overhead
3.1 GB
OS
0.0 GB
Free
19.3 GB
Memory
365 GB of 384 GB
Context
44K tokens · auto
Speed
76 tok/s · 63 when full
First reply
0.5 s for a 2K prompt
Running cost
$33/mo at home · $574/mo on a cloud 8× A40

Validation: Validated

What Kimi K2.6 on 4× RTX PRO 6000 Blackwell was checked against
CheckTargetResultStatus
Fits in GPU memory384 GB usable365 GB neededPass
Headroom5% free19.3 GB free (5%)Pass
Context for chat16K or more44KPass
Writing speed15 tok/s or more76 tok/sPass
First replyunder 3 s, 2K prompt0.5 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
2-bit (Q2_K)
Context
44K, auto
Chats at once
1
Use
Chat
Runs in
Ollama / LM Studio
Hardware
4× RTX PRO 6000 Blackwell
GPU can use
384 GB of 384 GB

Worth trying

  • 8-bit cache: Room for 80K context

Running cost

At home
$33/mo
1520 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 22, 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 4× RTX PRO 6000 Blackwell run?

Other models that run on 4× RTX PRO 6000 Blackwell

Questions

Can Kimi K2.6 run on 4× RTX PRO 6000 Blackwell?

Kimi K2.6 at 2-bit runs on the 4× RTX PRO 6000 Blackwell with 44K of context at about 76 tokens a second.

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