Hy3 on 2× RTX PRO 6000 Blackwell: VRAM, speed and fit
Hy3 at 4-bit runs on the 2× RTX PRO 6000 Blackwell with 44K of context at about 67 tokens a second.
Text generation · Chat · Ollama / LM Studio
Runs comfortably · on 2× RTX PRO 6000 Blackwell · 4-bit (Q4_K_M) · Ollama / LM Studio · Chat
- GPU memory
- 182 GB
- of 192 GB
- Context
- 44K
- auto
- Speed
- 67 tok/s
- 37 when full
- First reply
- 0.6 s
- 2K prompt
Where the memory goes
- Model
- 167 GB
- Context
- 13.8 GB
- Overhead
- 1.4 GB
- OS
- 0.0 GB
- Free
- 10.3 GB
- Memory
- 182 GB of 192 GB
- Context
- 44K tokens · auto
- Speed
- 67 tok/s · 37 when full
- First reply
- 0.6 s for a 2K prompt
- Running cost
- $18/mo at home · $287/mo on a cloud 4× A40
Validation: Validated
| Check | Target | Result | Status |
|---|---|---|---|
| Fits in GPU memory | 192 GB usable | 182 GB needed | Pass |
| Headroom | 5% free | 10.3 GB free (5%) | Pass |
| Context for chat | 16K or more | 44K | Pass |
| Writing speed | 15 tok/s or more | 67 tok/s | Pass |
| First reply | under 3 s, 2K prompt | 0.6 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
- 4-bit (Q4_K_M)
- Context
- 44K, auto
- Chats at once
- 1
- Use
- Chat
- Runs in
- Ollama / LM Studio
- Hardware
- 2× RTX PRO 6000 Blackwell
- GPU can use
- 192 GB of 192 GB
Worth trying
- 8-bit cache: Room for 80K context
Running cost
- At home
- $18/mo
- 800 W at the wall
- Renting instead
- $287/mo
- 4× A40 at $2.36/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 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
- RTX SparkRuns
- DGX SparkRuns
- Dual DGX SparkRuns
- DGX Station GB300Runs
- 4× RTX PRO 6000 BlackwellRuns
- 8× RTX PRO 6000 BlackwellRuns
- A100 80 GB SXMToo big
- H100 SXMToo big
All machines: Hy3 VRAM requirements. Everything that runs here: what can the 2× RTX PRO 6000 Blackwell run?
Other models that run on 2× RTX PRO 6000 Blackwell
Questions
Can Hy3 run on 2× RTX PRO 6000 Blackwell?
Hy3 at 4-bit runs on the 2× RTX PRO 6000 Blackwell with 44K of context at about 67 tokens a second.
Report VR-1IH6WCN, calculated Nov 22, 2026 from published specs, not benchmarked.