Kimi K2.6 on 4× H200 NVL: VRAM, speed and fit
Kimi K2.6 at 3-bit runs on the 4× H200 NVL with 256K of context at about 120 tokens a second.
Text generation · Chat · Ollama / LM Studio
Runs comfortably · on 4× H200 NVL · 3-bit (Q3_K_M) · Ollama / LM Studio · Chat
- GPU memory
- 488 GB
- of 564 GB
- Context
- 256K
- auto
- Speed
- 120 tok/s
- 72 when full
- First reply
- 0.5 s
- 2K prompt
Where the memory goes
- Model
- 467 GB
- Context
- 17.2 GB
- Overhead
- 3.1 GB
- OS
- 0.0 GB
- Free
- 76.3 GB
- Memory
- 488 GB of 564 GB
- Context
- 256K tokens · auto
- Speed
- 120 tok/s · 72 when full
- First reply
- 0.5 s for a 2K prompt
- Running cost
- $33/mo at home · $1,162/mo on a cloud 4× MI300X
Validation: Validated
| Check | Target | Result | Status |
|---|---|---|---|
| Fits in GPU memory | 564 GB usable | 488 GB needed | Pass |
| Headroom | 5% free | 76.3 GB free (14%) | Pass |
| Context for chat | 16K or more | 256K | Pass |
| Writing speed | 15 tok/s or more | 120 tok/s | Pass |
| First reply | under 3 s, 2K prompt | 0.5 s | Pass |
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
- 3-bit (Q3_K_M)
- Context
- 256K, auto
- Chats at once
- 1
- Use
- Chat
- Runs in
- Ollama / LM Studio
- Hardware
- 4× H200 NVL
- GPU can use
- 564 GB of 564 GB
Running cost
- At home
- $33/mo
- 1520 W at the wall
- Renting instead
- $1,162/mo
- 4× MI300X at $9.56/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- Model card
- huggingface.co/moonshotai/Kimi-K2.6
Kimi K2.6 on similar machines
- 4× RTX PRO 6000 BlackwellRuns
- 8× RTX PRO 6000 BlackwellRuns
- A100 80 GB SXMToo big
- H100 SXMToo big
- 8× H200 NVLRuns
All machines: Kimi K2.6 VRAM requirements. Everything that runs here: what can the 4× H200 NVL run?
Other models that run on 4× H200 NVL
Questions
Can Kimi K2.6 run on 4× H200 NVL?
Kimi K2.6 at 3-bit runs on the 4× H200 NVL with 256K of context at about 120 tokens a second.
Report VR-0I7HE2X, calculated Nov 22, 2026 from published specs, not benchmarked.