Can Hy3 run on AMD Instinct MI350X 288GB?

YES — Runs Great

S96Excellent

Estimated from fit model

Hy3 needs ~214.5 GB VRAM. AMD Instinct MI350X 288GB has 288.0 GB. With Q4_K_M quantization, expect ~91 tok/s.

Runtime: llama.cppCapacity: RoomyBandwidth: HighStack: StandardBottleneck: Balanced

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) — 214.5 GB, 98.9 tok/s, Runs well

214.5 GB required288.0 GB available

74% VRAM used

Fit status

Runs well

Decode

98.9 tok/s

TTFT

1958 ms

Safe context

257K

Memory

214.5 GB / 288.0 GB

Memory breakdown

Weights180.0 GB

KV Cache4.9 GB

Runtime0.9 GB

Headroom28.8 GB

See how fast it feels

See how fast it feelsHy3 on AMD Instinct MI350X 288GB
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: 98.9 tok/s decode · 2.0s TTFT (warm) · 247 tok/s prefill

What limits this setup

This setup is broadly balanced for this model.

No major red flags

This recommendation has enough memory headroom and acceptable estimated speed for the selected workload.

Best improvement path

Performance by workload

Workload	Grade	Fit	Decode	TTFT	Context
Chat	S	Runs well	90.9 tok/s	1161 ms	257K
Coding	S	Runs well	90.9 tok/s	2129 ms	257K
Agentic Coding	S	Runs well	90.9 tok/s	3097 ms	257K
Reasoning	S	Runs well	90.9 tok/s	2517 ms	257K
RAG	S	Runs well	90.9 tok/s	3872 ms	257K

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 AMD Instinct MI350X 288GB (288.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q1_0_G128	1.125	42.5 GB	Very Low	A78
Q2_0_G128	1.71	78.8 GB	Low	A81
Q2_K	2	115.1 GB	Low	A84
Q3_K_S	3	144.6 GB	Low	S86
NVFP4	4	165.2 GB	Medium	S87
Q4_K_M	4	180.0 GB	Medium	S87
Q5_K_MBest for your GPU	5	212.4 GB	High	S87
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

Your hardware

More models your AMD Instinct MI350X 288GB can run

Model	Params	Grade	Decode	Capabilities
Qwen 3.5 397B A17B	397B	S	78.9 tok/s

Frequently asked questions

Can AMD Instinct MI350X 288GB run Hy3?

Yes, AMD Instinct MI350X 288GB can run Hy3 with a S grade (Runs well). Expected decode speed: 90.9 tok/s.

How much VRAM does Hy3 need?

Hy3 (295B parameters) requires approximately 214.5 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 AMD Instinct MI350X 288GB?

On AMD Instinct MI350X 288GB, Hy3 achieves approximately 90.9 tokens per second decode speed with a time-to-first-token of 2129ms using Q4_K_M quantization.

Can AMD Instinct MI350X 288GB run Hy3 for coding?

For coding workloads, Hy3 on AMD Instinct MI350X 288GB receives a S grade with 90.9 tok/s and 257K context.

What context window can Hy3 use on AMD Instinct MI350X 288GB?

On AMD Instinct MI350X 288GB, Hy3 can safely use up to 257K tokens of context. The model's official context limit is 262K, but available memory constrains the safe maximum.

See all results for AMD Instinct MI350X 288GB 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-instinct-mi350x-288gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>

Preview: