Can Hy3 run on NVIDIA B200 180GB?

BARELY — Tight on Memory

A82Great

Estimated from fit model

Hy3 needs ~203.7 GB VRAM. NVIDIA B200 180GB has 180.0 GB. With Q4_K_M quantization, expect ~73 tok/s.

Runtime: llama.cppCapacity: OffloadBandwidth: HighStack: StandardBottleneck: Host offload

Operating mode

Choose the run profile you care about

Interactive favors responsiveness, while light API and scale-out lean harder on serving readiness. The fit stays the same, but the recommendation lens changes.

Current mode

Balanced

Balanced for general local use. Keeps the ranking neutral across personal and serving workflows.

Capabilities:

Select quantization to explore

Q4_K_M (Medium quality) — 203.7 GB, 79.1 tok/s, Very compromised (needs ~21 GB host RAM)

203.7 GB required180.0 GB available

113% VRAM needed

23.7 GB over capacity — needs offload or smaller quantization

Fit status

Very compromised (needs ~21 GB host RAM)

Decode

79.1 tok/s

TTFT

2447 ms

Safe context

Memory

203.7 GB / 180.0 GB

Offload

10%

Memory breakdown

Weights180.0 GB

KV Cache4.9 GB

Runtime0.9 GB

Headroom18.0 GB

See how fast it feels

See how fast it feelsHy3 on NVIDIA B200 180GB
1st promptCold start — includes initialization
>Solve: If a train travels at 60 mph for 2.5 hours, how far does it go?
Let me work through this step by step.

Given information:
  - Speed = 60 mph (miles per hour)
  - Time  = 2.5 hours

Formula: Distance = Speed x Time

Calculation:
  Distance = 60 mph x 2.5 h
           = 150 miles

The train travels 150 miles.

Double-check: at 60 mph the train covers 60 miles each hour. In half an hour it covers 30 miles. So in 2.5 hours: 60 + 60 + 30 = 150 miles. Confirmed.
2nd promptWarm — model ready, no init overhead
>What if the train stops for 20 minutes halfway?
The stop doesn't change the total distance covered while moving, but it affects total trip time.

Breakdown:
  - First half: 1.25 hours at 60 mph = 75 miles
  - Stop: 20 minutes (no distance)
  - Second half: 1.25 hours at 60 mph = 75 miles

Total distance: 150 miles (same)
Total time: 2.5 h + 0.33 h = 2.83 hours
Average speed: 150 / 2.83 = 53 mph

The distance stays the same but average speed drops to 53 mph because of the stop.
Estimated: 79.1 tok/s decode · 2.4s TTFT (warm) · 198 tok/s prefill

What limits this setup

It fits through host-memory offload, and offload is the main reason performance drops.

CPU or host-memory offload is active

About 10% of the working set spills out of accelerator memory, which usually hurts latency and sustained decode throughput.

Very little memory headroom

You can run the model, but there is not much room left for longer context, bigger batches, extra apps, or future model updates.

Best improvement path

Remove offload with more accelerator memory

Prioritize a GPU or unified-memory tier that fits the whole model natively. Removing offload usually helps more than small compute gains.

Buy headroom, not only minimum fit

A slightly larger memory tier gives you safer context growth and makes the recommendation more future-proof.

Increase host RAM if you keep offloading

This setup may need roughly {ram} GB of extra host RAM just for the offloaded portion, before OS and other tools.

Performance by workload

Workload	Grade	Fit	Decode	TTFT	Context
Chat	A	Very compromised	74.2 tok/s	1423 ms	4K
Coding	A	Very compromised	72.7 tok/s	2661 ms	4K
Agentic Coding	A	Very compromised	70.0 tok/s	4026 ms	4K
Reasoning	A	Very compromised	72.7 tok/s	3145 ms	4K
RAG	A	Very compromised	70.0 tok/s	5032 ms	4K

Inference speed

Hy3 inference speed — tokens per second by GPU & Mac

Estimated decode speed (tokens/sec) for Hy3 at Q4_K_M across popular GPUs and Apple Silicon, including multi-GPU rigs, using the fastest local runtime per device. Fastest is Mac Studio M3 Ultra 256GB at ~12 tok/s. Speed is memory-bandwidth bound, so cards that fit the whole model in VRAM run far faster than ones that offload to system RAM.

GPU / Mac	Memory	Quant	Speed (tok/s)	Fits?
Mac Studio M3 Ultra 256GB	256 GB	Q4_K_M	11.6	Heavy offload
Mac Studio M2 Ultra 128GB	128 GB	Q4_K_M	5.5	Too big
Mac Studio M1 Ultra 128GB	128 GB	Q4_K_M	5.2	Too big
MacBook Pro M4 Max 128GB	128 GB	Q4_K_M	4.1	Too big
MacBook Pro M4 Max 64GB	64 GB	Q4_K_M	4.1	Too big
RTX 5090 32GB	32 GB	Q4_K_M	3.0	Too big
2× RX 7900 XTX 24GB	48 GB	Q4_K_M	3.0	Too big
MacBook Pro M3 Max 64GB	64 GB	Q4_K_M	2.8	Too big
MacBook Pro M1 Max 64GB	64 GB	Q4_K_M	2.6	Too big
MacBook Pro M4 Pro 48GB	48 GB	Q4_K_M	2.5	Too big
2× RTX 4090 24GB	48 GB	Q4_K_M	2.1	Too big
RTX 4090 24GB	24 GB	Q4_K_M	2.0	Too big
RTX 4080 Super 16GB	16 GB	Q4_K_M	2.0	Too big
RTX 3090 24GB	24 GB	Q4_K_M	2.0	Too big
RTX 4070 12GB	12 GB	Q4_K_M	2.0	Too big
RTX 3060 12GB	12 GB	Q4_K_M	2.0	Too big
RTX 4060 8GB	8 GB	Q4_K_M	2.0	Too big
RX 7900 XTX 24GB	24 GB	Q4_K_M	2.0	Too big
2× RTX 3090 24GB	48 GB	Q4_K_M	2.0	Too big
4× RTX 3060 12GB	48 GB	Q4_K_M	2.0	Too big

Estimates for single-stream decoding at Q4_K_M; real tokens/sec varies with prompt length, context, batch size, and runtime build. Prompt processing (prefill) is faster than the decode figures shown here.

Quantization options

How Hy3 (295B params) fits at each quantization level on NVIDIA B200 180GB (180.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q1_0_G128	1.125	42.5 GB	Very Low	A81
Q2_0_G128	1.71	78.8 GB	Low	S85
Q2_KBest for your GPU	2	115.1 GB	Low	S87
Q3_K_S	3	144.6 GB	Low	F0
NVFP4	4	165.2 GB	Medium	F0
Q4_K_M	4	180.0 GB	Medium	F0
Q5_K_M	5	212.4 GB	High	F0
Q6_K	6	241.9 GB	High	F0
Q8_0	8	315.7 GB	Very High	F0
F16	16	604.8 GB	Maximum	F0

Get started

Copy-paste commands to run Hy3 on your machine.

Run

docker run --rm -it ghcr.io/ggerganov/llama.cpp:full \
  --hf-repo "tencent/Hy3" \
  --hf-file "Hy3-Q4_K_M.gguf" \
  -c 4096 -ngl 99

Frequently asked questions

Can NVIDIA B200 180GB run Hy3?

Yes, NVIDIA B200 180GB can run Hy3 with a A grade (Very compromised). Expected decode speed: 72.7 tok/s.

How much VRAM does Hy3 need?

Hy3 (295B parameters) requires approximately 203.7 GB of memory with Q4_K_M quantization.

What is the best quantization for Hy3?

The recommended quantization for Hy3 is Q4_K_M, which balances quality and memory efficiency.

What speed will Hy3 run at on NVIDIA B200 180GB?

On NVIDIA B200 180GB, Hy3 achieves approximately 72.7 tokens per second decode speed with a time-to-first-token of 2661ms using Q4_K_M quantization.

Can NVIDIA B200 180GB run Hy3 for coding?

For coding workloads, Hy3 on NVIDIA B200 180GB receives a A grade with 72.7 tok/s and 4K context.

What context window can Hy3 use on NVIDIA B200 180GB?

On NVIDIA B200 180GB, Hy3 can safely use up to 4K tokens of context. The model's official context limit is 262K, but available memory constrains the safe maximum.

What should I upgrade first if Hy3 feels slow on NVIDIA B200 180GB?

Remove offload with more accelerator memory. Prioritize a GPU or unified-memory tier that fits the whole model natively. Removing offload usually helps more than small compute gains.

See all results for NVIDIA B200 180GB See all hardware for Hy3

Embed this result▼

Paste this snippet into any page to show a live fit card.

<iframe src="https://willitrunai.com/embed/hy3-on-b200-180gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>

Preview: