Skip to content

Hy3 on 4× RTX PRO 6000 Blackwell: VRAM, speed and fit

Hy3 at 8-bit runs on the 4× RTX PRO 6000 Blackwell with 224K of context at about 44 tokens a second.

Text generation · Chat · Ollama / LM Studio

Runs comfortably · on 4× RTX PRO 6000 Blackwell · 8-bit (Q8_0) · Ollama / LM Studio · Chat

GPU memory
365 GB
of 384 GB
Context
224K
auto
Speed
44 tok/s
12 when full
First reply
0.3 s
2K prompt

Where the memory goes

Model
292 GB
Context
70.0 GB
Overhead
2.7 GB
OS
0.0 GB
Free
19.4 GB
Memory
365 GB of 384 GB
Context
224K tokens · auto
Speed
44 tok/s · 12 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

What Hy3 on 4× RTX PRO 6000 Blackwell was checked against
CheckTargetResultStatus
Fits in GPU memory384 GB usable365 GB neededPass
Headroom5% free19.4 GB free (5%)Pass
Context for chat16K or more224KPass
Writing speed15 tok/s or more44 tok/sPass
First replyunder 3 s, 2K prompt0.3 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
Hy3
Parameters
295B, 21B active
Precision
8-bit (Q8_0)
Context
224K, 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

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 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

Hy3 on similar machines

Other models that run on 4× RTX PRO 6000 Blackwell

Questions

Can Hy3 run on 4× RTX PRO 6000 Blackwell?

Hy3 at 8-bit runs on the 4× RTX PRO 6000 Blackwell with 224K of context at about 44 tokens a second.

Report VR-1Y4M98U, calculated Nov 22, 2026 from published specs, not benchmarked.