Can Phi 3 Medium 14B run on AMD Instinct MI350X 288GB?

YES — Runs Great

B56Good

Estimated from fit model

Phi 3 Medium 14B needs ~41.3 GB VRAM. AMD Instinct MI350X 288GB has 288.0 GB. With Q4_K_M quantization, expect ~196 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) — 41.3 GB, 196.0 tok/s, Runs well

41.3 GB required288.0 GB available

14% VRAM used

Fit status

Runs well

Decode

196.0 tok/s

TTFT

988 ms

Safe context

128K

Memory

41.3 GB / 288.0 GB

Memory breakdown

Weights8.5 GB

KV Cache3.1 GB

Runtime0.9 GB

Headroom28.8 GB

See how fast it feels

See how fast it feelsPhi 3 Medium 14B 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: 196.0 tok/s decode · 988ms TTFT (warm) · 490 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	B	Runs well	196.0 tok/s	539 ms	128K
Coding	B	Runs well	196.0 tok/s	988 ms	128K
Agentic Coding	B	Runs well	196.0 tok/s	1437 ms	128K
Reasoning	B	Runs well	196.0 tok/s	1167 ms	128K
RAG	B	Runs well	196.0 tok/s	1796 ms	128K

Inference speed

Phi 3 Medium 14B inference speed — tokens per second by GPU & Mac

Estimated decode speed (tokens/sec) for Phi 3 Medium 14B at Q4_K_M across popular GPUs and Apple Silicon, using the fastest local runtime per device. Fastest is RTX 5090 32GB at ~151 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?
RTX 5090 32GB	32 GB	Q4_K_M	151.1	Fits
RTX 4090 24GB	24 GB	Q4_K_M	96.4	Fits
RX 7900 XTX 24GB	24 GB	Q4_K_M	87.0	Fits
RTX 3090 24GB	24 GB	Q4_K_M	82.5	Fits
RTX 4080 Super 16GB	16 GB	Q4_K_M	80.7	Tight
Mac Studio M3 Ultra 256GB	256 GB	Q4_K_M	70.1	Fits
Mac Studio M2 Ultra 128GB	128 GB	Q4_K_M	58.4	Fits
Mac Studio M1 Ultra 128GB	128 GB	Q4_K_M	55.4	Fits
MacBook Pro M4 Max 128GB	128 GB	Q4_K_M	38.1	Fits
MacBook Pro M4 Max 64GB	64 GB	Q4_K_M	38.1	Fits
MacBook Pro M3 Max 64GB	64 GB	Q4_K_M	30.2	Fits
RTX 4070 12GB	12 GB	Q4_K_M	28.4	Heavy offload
MacBook Pro M1 Max 64GB	64 GB	Q4_K_M	27.7	Fits
MacBook Pro M4 Pro 48GB	48 GB	Q4_K_M	23.3	Fits
RTX 3060 12GB	12 GB	Q4_K_M	16.7	Heavy offload
RTX 4060 8GB	8 GB	Q4_K_M	6.1	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 Phi 3 Medium 14B (14B params) fits at each quantization level on AMD Instinct MI350X 288GB (288.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	5.5 GB	Low	C47
Q3_K_S	3	6.9 GB	Low	C47
NVFP4	4	7.8 GB	Medium	C47
Q4_K_M	4	8.5 GB	Medium	C47
Q5_K_M	5	10.1 GB	High	C47
Q6_K	6	11.5 GB	High	C47
Q8_0	8	15.0 GB	Very High	C47
F16Best for your GPU	16	28.7 GB	Maximum	C48

Get started

Copy-paste commands to run Phi 3 Medium 14B on your machine.

Run

ollama run phi3:medium

Frequently asked questions

Can AMD Instinct MI350X 288GB run Phi 3 Medium 14B?

Yes, AMD Instinct MI350X 288GB can run Phi 3 Medium 14B with a B grade (Runs well). Expected decode speed: 196.0 tok/s.

How much VRAM does Phi 3 Medium 14B need?

Phi 3 Medium 14B (14B parameters) requires approximately 41.3 GB of memory with Q4_K_M quantization.

What is the best quantization for Phi 3 Medium 14B?

The recommended quantization for Phi 3 Medium 14B is Q4_K_M, which balances quality and memory efficiency.

What speed will Phi 3 Medium 14B run at on AMD Instinct MI350X 288GB?

On AMD Instinct MI350X 288GB, Phi 3 Medium 14B achieves approximately 196.0 tokens per second decode speed with a time-to-first-token of 988ms using Q4_K_M quantization.

Can AMD Instinct MI350X 288GB run Phi 3 Medium 14B for coding?

For coding workloads, Phi 3 Medium 14B on AMD Instinct MI350X 288GB receives a B grade with 196.0 tok/s and 128K context.

What context window can Phi 3 Medium 14B use on AMD Instinct MI350X 288GB?

On AMD Instinct MI350X 288GB, Phi 3 Medium 14B can safely use up to 128K tokens of context. The model's official context limit is 128K, but available memory constrains the safe maximum.

See all results for AMD Instinct MI350X 288GB See all hardware for Phi 3 Medium 14B

Embed this result▼

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

<iframe src="https://willitrunai.com/embed/phi-3-medium-14b-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: