Will It Run AI

Can DeepSeek R1 Distill 32B run on Gaudi 3 128GB?

YES — Runs Great

A73Great
Estimated from fit model

DeepSeek R1 Distill 32B needs ~37.1 GB VRAM. Gaudi 3 128GB has 128.0 GB. With Q4_K_M quantization, expect ~133 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) — 37.1 GB, 143.3 tok/s, Runs well
37.1 GB required128.0 GB available
29% VRAM used

Fit status

Runs well

Decode

143.3 tok/s

TTFT

1351 ms

Safe context

33K

Memory

37.1 GB / 128.0 GB

Memory breakdown

Weights19.5 GB
KV Cache3.9 GB
Runtime0.9 GB
Headroom12.8 GB

See how fast it feels

See how fast it feelsDeepSeek R1 Distill 32B on Gaudi 3 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: 143.3 tok/s decode · 1.4s TTFT (warm) · 358 tok/s prefill

What limits this setup

The raw memory story may look fine, but the software ecosystem is still a constraint here.

Runtime ecosystem is narrower than CUDA

Intel GPUs can look attractive on memory per dollar, but local AI tooling, kernels, and model coverage are still broader and easier on CUDA today.

Best improvement path

Prefer CUDA if you want the path of least resistance

If your goal is maximum runtime coverage, easier troubleshooting, and better support for new local AI releases, CUDA is usually still the safer upgrade path.

Performance by workload

WorkloadGradeFitDecodeTTFTContext
ChatARuns well143.3 tok/s737 ms33K
CodingARuns well132.7 tok/s1459 ms33K
Agentic CodingARuns well143.3 tok/s1965 ms33K
ReasoningARuns well143.3 tok/s1597 ms33K
RAGARuns well143.3 tok/s2456 ms33K

Quantization options

How DeepSeek R1 Distill 32B (32B params) fits at each quantization level on Gaudi 3 128GB (128.0 GB usable).

QuantBitsVRAMQualityFit
Q2_K
2
12.5 GB
LowB64
Q3_K_S
3
15.7 GB
LowB64
NVFP4
4
17.9 GB
MediumB64
Q4_K_M
4
19.5 GB
MediumB64
Q5_K_M
5
23.0 GB
HighB65
Q6_K
6
26.2 GB
HighB65
Q8_0
8
34.2 GB
Very HighB67
F16Best for your GPU
16
65.6 GB
MaximumA72

Get started

Copy-paste commands to run DeepSeek R1 Distill 32B on your machine.

Run

ollama run deepseek-r1:32b

Your hardware

More models your Gaudi 3 128GB can run

ModelParamsGradeDecodeCapabilities
MistralDevstral 2 123B Instruct123BS37.5 tok/s
AlibabaQwen 3.5 122B A10B122BS104.1 tok/s
AlibabaQwen 3.6 35B A3B35BS329.1 tok/s
AlibabaQwen 3.5 35B A3B35BS357.9 tok/s
MistralMistral Small 4 119B119BS112.9 tok/s

Frequently asked questions

Can Gaudi 3 128GB run DeepSeek R1 Distill 32B?

Yes, Gaudi 3 128GB can run DeepSeek R1 Distill 32B with a A grade (Runs well). Expected decode speed: 132.7 tok/s.

How much VRAM does DeepSeek R1 Distill 32B need?

DeepSeek R1 Distill 32B (32B parameters) requires approximately 37.1 GB of memory with Q4_K_M quantization.

What is the best quantization for DeepSeek R1 Distill 32B?

The recommended quantization for DeepSeek R1 Distill 32B is Q4_K_M, which balances quality and memory efficiency.

What speed will DeepSeek R1 Distill 32B run at on Gaudi 3 128GB?

On Gaudi 3 128GB, DeepSeek R1 Distill 32B achieves approximately 132.7 tokens per second decode speed with a time-to-first-token of 1459ms using Q4_K_M quantization.

Can Gaudi 3 128GB run DeepSeek R1 Distill 32B for coding?

For coding workloads, DeepSeek R1 Distill 32B on Gaudi 3 128GB receives a A grade with 132.7 tok/s and 33K context.

What context window can DeepSeek R1 Distill 32B use on Gaudi 3 128GB?

On Gaudi 3 128GB, DeepSeek R1 Distill 32B can safely use up to 33K tokens of context. The model's official context limit is 33K, but available memory constrains the safe maximum.

What should I upgrade first if DeepSeek R1 Distill 32B feels slow on Gaudi 3 128GB?

Prefer CUDA if you want the path of least resistance. If your goal is maximum runtime coverage, easier troubleshooting, and better support for new local AI releases, CUDA is usually still the safer upgrade path.

Would CUDA be a better path than Gaudi 3 128GB for DeepSeek R1 Distill 32B?

Often yes, if your goal is the easiest setup and the widest runtime support. Intel can offer attractive memory capacity, but CUDA still tends to win on tooling maturity, guides, kernels, and model coverage for local AI.

See all results for Gaudi 3 128GBSee all hardware for DeepSeek R1 Distill 32B
Embed this result▼

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

<iframe src="https://willitrunai.com/embed/deepseek-r1-distill-32b-on-gaudi-3-128gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>

Preview: