willitrun·ai

Can Qwen 3 32B run on Radeon PRO W7900 DS 48GB?

YES — Runs Great

S92Excellent
Estimated from fit model

Qwen 3 32B needs ~29.1 GB VRAM. Radeon PRO W7900 DS 48GB has 48.0 GB. With Q4_K_M quantization, expect ~28 tok/s.

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

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) — 29.1 GB, 28.4 tok/s, Runs well
29.1 GB required48.0 GB available
61% VRAM used

Fit status

Runs well

Decode

28.4 tok/s

TTFT

6817 ms

Safe context

93K

Memory

29.1 GB / 48.0 GB

Memory breakdown

Weights19.5 GB
KV Cache3.9 GB
Runtime0.9 GB
Headroom4.8 GB

See how fast it feels

See how fast it feelsQwen 3 32B on Radeon PRO W7900 DS 48GB
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: 28.4 tok/s decode · 6.8s TTFT (warm) · 71 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

WorkloadGradeFitDecodeTTFTContext
ChatSRuns well28.4 tok/s3718 ms93K
CodingSRuns well28.4 tok/s6817 ms93K
Agentic CodingSRuns well28.4 tok/s9916 ms93K
ReasoningSRuns well28.4 tok/s8056 ms93K
RAGSRuns well28.4 tok/s12394 ms93K

Inference speed

Qwen 3 32B inference speed — tokens per second by GPU & Mac

Estimated decode speed (tokens/sec) for Qwen 3 32B at Q4_K_M across popular GPUs and Apple Silicon, using the fastest local runtime per device. Fastest is RTX 5090 32GB at ~67 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 / MacMemoryQuantSpeed (tok/s)Fits?
NVIDIARTX 5090 32GB
32 GBQ4_K_M66.9Tight
MacBook Pro M4 Max 128GB
128 GBQ4_K_M33.5Fits
MacBook Pro M4 Max 64GB
64 GBQ4_K_M33.5Fits
Mac Studio M3 Ultra 256GB
256 GBQ4_K_M31.0Fits
Mac Studio M2 Ultra 128GB
128 GBQ4_K_M25.9Fits
NVIDIARTX 4090 24GB
24 GBQ4_K_M24.9Heavy offload
Mac Studio M1 Ultra 128GB
128 GBQ4_K_M24.5Fits
RX 7900 XTX 24GB
24 GBQ4_K_M23.0Heavy offload
NVIDIARTX 3090 24GB
24 GBQ4_K_M21.3Heavy offload
MacBook Pro M4 Pro 48GB
48 GBQ4_K_M21.1Tight
MacBook Pro M3 Max 64GB
64 GBQ4_K_M13.4Fits
MacBook Pro M1 Max 64GB
64 GBQ4_K_M12.3Fits
NVIDIARTX 4080 Super 16GB
16 GBQ4_K_M9.0Too big
NVIDIARTX 4070 12GB
12 GBQ4_K_M3.2Too big
NVIDIARTX 3060 12GB
12 GBQ4_K_M2.0Too big
NVIDIARTX 4060 8GB
8 GBQ4_K_M2.0Too 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 32B (32B params) fits at each quantization level on Radeon PRO W7900 DS 48GB (48.0 GB usable).

QuantBitsVRAMQualityFit
Q2_K
2
12.5 GB
LowA85
Q3_K_S
3
15.7 GB
LowS86
NVFP4
4
17.9 GB
MediumS86
Q4_K_M
4
19.5 GB
MediumS87
Q5_K_M
5
23.0 GB
HighS88
Q6_K
6
26.2 GB
HighS89
Q8_0Best for your GPU
8
34.2 GB
Very HighS89
F16
16
65.6 GB
MaximumF0

Get started

Copy-paste commands to run Qwen 3 32B on your machine.

Run

ollama run qwen3:32b

Your hardware

More models your Radeon PRO W7900 DS 48GB can run

ModelParamsGradeDecodeCapabilities
AlibabaQwen 3.6 35B A3B35BS64.8 tok/s
AlibabaQwen 3.5 35B A3B35BS70.4 tok/s

Frequently asked questions

Can Radeon PRO W7900 DS 48GB run Qwen 3 32B?

Yes, Radeon PRO W7900 DS 48GB can run Qwen 3 32B with a S grade (Runs well). Expected decode speed: 28.4 tok/s.

How much VRAM does Qwen 3 32B need?

Qwen 3 32B (32B parameters) requires approximately 29.1 GB of memory with Q4_K_M quantization.

What is the best quantization for Qwen 3 32B?

The recommended quantization for Qwen 3 32B is Q4_K_M, which balances quality and memory efficiency.

What speed will Qwen 3 32B run at on Radeon PRO W7900 DS 48GB?

On Radeon PRO W7900 DS 48GB, Qwen 3 32B achieves approximately 28.4 tokens per second decode speed with a time-to-first-token of 6817ms using Q4_K_M quantization.

Can Radeon PRO W7900 DS 48GB run Qwen 3 32B for coding?

For coding workloads, Qwen 3 32B on Radeon PRO W7900 DS 48GB receives a S grade with 28.4 tok/s and 93K context.

What context window can Qwen 3 32B use on Radeon PRO W7900 DS 48GB?

On Radeon PRO W7900 DS 48GB, Qwen 3 32B can safely use up to 93K tokens of context. The model's official context limit is 131K, but available memory constrains the safe maximum.

See all results for Radeon PRO W7900 DS 48GBSee all hardware for Qwen 3 32B
Embed this result▼

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

<iframe src="https://willitrunai.com/embed/qwen-3-32b-on-radeon-pro-w7900-ds-48gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>

Preview: