Hy3 on 4× H200 NVL: VRAM, speed and fit
Hy3 at 8-bit runs on the 4× H200 NVL with 256K of context at about 87 tokens a second.
Text generation · Chat · Ollama / LM Studio
Runs comfortably · on 4× H200 NVL · 8-bit (Q8_0) · Ollama / LM Studio · Chat
- GPU memory
- 375 GB
- of 564 GB
- Context
- 256K
- auto
- Speed
- 87 tok/s
- 27 when full
- First reply
- 0.3 s
- 2K prompt
Where the memory goes
- Model
- 292 GB
- Context
- 80.0 GB
- Overhead
- 2.7 GB
- OS
- 0.0 GB
- Free
- 189 GB
- Memory
- 375 GB of 564 GB
- Context
- 256K tokens · auto
- Speed
- 87 tok/s · 27 when full
- First reply
- 0.3 s for a 2K prompt
- Running cost
- $33/mo at home · $574/mo on a cloud 8× A40
Validation: Validated
| Check | Target | Result | Status |
|---|---|---|---|
| Fits in GPU memory | 564 GB usable | 375 GB needed | Pass |
| Headroom | 5% free | 189 GB free (34%) | Pass |
| Context for chat | 16K or more | 256K | Pass |
| Writing speed | 15 tok/s or more | 87 tok/s | Pass |
| First reply | under 3 s, 2K prompt | 0.3 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
- Hy3
- Parameters
- 295B, 21B active
- Precision
- 8-bit (Q8_0)
- 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
- $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 bartowski/Hy3-GGUF- vLLM
vllm serve tencent/Hy3- MLX (Mac)
mlx_lm.chat --model mlx-community/Hy3-OptiQ-2bit- Model card
- huggingface.co/tencent/Hy3
Hy3 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: Hy3 VRAM requirements. Everything that runs here: what can the 4× H200 NVL run?
Other models that run on 4× H200 NVL
Questions
Can Hy3 run on 4× H200 NVL?
Hy3 at 8-bit runs on the 4× H200 NVL with 256K of context at about 87 tokens a second.
Report VR-0VTFE78, calculated Nov 22, 2026 from published specs, not benchmarked.