Can Qwen 3 30B A3B run on AMD Instinct MI300A 128GB?

YES — Runs Great

S88Excellent

Estimated from fit model

Qwen 3 30B A3B needs ~33.8 GB VRAM. AMD Instinct MI300A 128GB has 128.0 GB. With Q4_K_M quantization, expect ~561 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) — 33.8 GB, 561.0 tok/s, Runs well

33.8 GB required128.0 GB available

26% VRAM used

Fit status

Runs well

Decode

561.0 tok/s

TTFT

350 ms

Safe context

131K

Memory

33.8 GB / 128.0 GB

Memory breakdown

Weights18.6 GB

KV Cache1.5 GB

Runtime0.9 GB

Headroom12.8 GB

See how fast it feels

See how fast it feelsQwen 3 30B A3B on AMD Instinct MI300A 128GB
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: 561.0 tok/s decode · 350ms TTFT (warm) · 1403 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	561.0 tok/s	350 ms	131K
Coding	S	Runs well	561.0 tok/s	350 ms	131K
Agentic Coding	S	Runs well	561.0 tok/s	502 ms	131K
Reasoning	S	Runs well	561.0 tok/s	408 ms	131K
RAG	S	Runs well	561.0 tok/s	627 ms	131K

Inference speed

Qwen 3 30B A3B inference speed — tokens per second by GPU & Mac

Estimated decode speed (tokens/sec) for Qwen 3 30B A3B at Q4_K_M across popular GPUs and Apple Silicon, using the fastest local runtime per device. Fastest is RTX 5090 32GB at ~182 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	181.6	Fits
RTX 4090 24GB	24 GB	Q4_K_M	115.8	Offloads
Mac Studio M3 Ultra 256GB	256 GB	Q4_K_M	109.5	Fits
RX 7900 XTX 24GB	24 GB	Q4_K_M	104.5	Offloads
RTX 3090 24GB	24 GB	Q4_K_M	99.1	Offloads
Mac Studio M2 Ultra 128GB	128 GB	Q4_K_M	91.2	Fits
Mac Studio M1 Ultra 128GB	128 GB	Q4_K_M	86.5	Fits
MacBook Pro M4 Max 128GB	128 GB	Q4_K_M	67.6	Fits
MacBook Pro M4 Max 64GB	64 GB	Q4_K_M	67.6	Fits
MacBook Pro M3 Max 64GB	64 GB	Q4_K_M	47.2	Fits
MacBook Pro M1 Max 64GB	64 GB	Q4_K_M	43.2	Fits
MacBook Pro M4 Pro 48GB	48 GB	Q4_K_M	41.3	Fits
RTX 4080 Super 16GB	16 GB	Q4_K_M	32.7	Too big
RTX 4070 12GB	12 GB	Q4_K_M	11.4	Too big
RTX 3060 12GB	12 GB	Q4_K_M	7.2	Too big
RTX 4060 8GB	8 GB	Q4_K_M	4.5	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 Qwen 3 30B A3B (30.5B params) fits at each quantization level on AMD Instinct MI300A 128GB (128.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	11.9 GB	Low	A79
Q3_K_S	3	14.9 GB	Low	A79
NVFP4	4	17.1 GB	Medium	A79
Q4_K_M	4	18.6 GB	Medium	A80
Q5_K_M	5	22.0 GB	High	A80
Q6_K	6	25.0 GB	High	A80
Q8_0	8	32.6 GB	Very High	A81
F16Best for your GPU	16	62.5 GB	Maximum	S86

Get started

Copy-paste commands to run Qwen 3 30B A3B on your machine.

Run

ollama run qwen3:30b-a3b

Your hardware

More models your AMD Instinct MI300A 128GB can run

Model	Params	Grade	Decode
Devstral 2 123B Instruct	123B	S	53.8 tok/s
Qwen 3.5 122B A10B	122B	S	149.2 tok/s
Qwen 3.6 35B A3B	35B	S	471.5 tok/s
Qwen 3.5 35B A3B	35B	S	512.7 tok/s
Qwen 3 32B	32B	S	206.7 tok/s

Frequently asked questions

Can AMD Instinct MI300A 128GB run Qwen 3 30B A3B?

Yes, AMD Instinct MI300A 128GB can run Qwen 3 30B A3B with a S grade (Runs well). Expected decode speed: 561.0 tok/s.

How much VRAM does Qwen 3 30B A3B need?

Qwen 3 30B A3B (30.5B parameters) requires approximately 33.8 GB of memory with Q4_K_M quantization.

What is the best quantization for Qwen 3 30B A3B?

The recommended quantization for Qwen 3 30B A3B is Q4_K_M, which balances quality and memory efficiency.

What speed will Qwen 3 30B A3B run at on AMD Instinct MI300A 128GB?

On AMD Instinct MI300A 128GB, Qwen 3 30B A3B achieves approximately 561.0 tokens per second decode speed with a time-to-first-token of 350ms using Q4_K_M quantization.

Can AMD Instinct MI300A 128GB run Qwen 3 30B A3B for coding?

For coding workloads, Qwen 3 30B A3B on AMD Instinct MI300A 128GB receives a S grade with 561.0 tok/s and 131K context.

What context window can Qwen 3 30B A3B use on AMD Instinct MI300A 128GB?

On AMD Instinct MI300A 128GB, Qwen 3 30B A3B can safely use up to 131K tokens of context. The model's official context limit is 131K, but available memory constrains the safe maximum.

See all results for AMD Instinct MI300A 128GB See all hardware for Qwen 3 30B A3B

Embed this result▼

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

<iframe src="https://willitrunai.com/embed/qwen-3-30b-a3b-on-instinct-mi300a-128gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>

Preview: