Can DeepSeek R1 671B run on AMD Instinct MI350X 288GB?

NO — Won't Fit

F0Won't run

Estimated from fit model

DeepSeek R1 671B needs ~498.6 GB but AMD Instinct MI350X 288GB only has 288.0 GB. Try a smaller quantization or lighter model.

Runtime: llama.cppCapacity: No fitBandwidth: HighStack: StandardBottleneck: Memory capacity

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) — 498.6 GB, exceeds 288.0 GB available

498.6 GB required288.0 GB available

173% VRAM needed

210.6 GB over capacity — needs offload or smaller quantization

Fit status

Too heavy

Decode

9.8 tok/s

TTFT

19765 ms

Safe context

Memory

498.6 GB / 288.0 GB

Offload

40%

Memory breakdown

Weights409.3 GB

KV Cache59.6 GB

Runtime0.9 GB

Headroom28.8 GB

See how fast it feels

With memory offload — actual speed may be lower

See how fast it feelsDeepSeek R1 671B 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: 9.8 tok/s decode · 19.8s TTFT (warm) · 25 tok/s prefill

What limits this setup

Usable VRAM is the main blocker for this model.

Not enough usable memory

The model needs 498.6 GB, but this setup only exposes 288.0 GB of usable VRAM.

Best improvement path

Add more VRAM headroom

The first useful upgrade is more dedicated VRAM so you can fit the model without shrinking context or dropping to a much lower quant.

Performance by workload

Workload	Grade	Fit	Decode	TTFT	Context
Chat	F	Too heavy	11.2 tok/s	9470 ms	4K
Coding	F	Too heavy	9.8 tok/s	19765 ms	4K
Agentic Coding	F	Too heavy	7.7 tok/s	36459 ms	4K
Reasoning	F	Too heavy	9.8 tok/s	23359 ms	4K
RAG	F	Too heavy	7.7 tok/s	45574 ms	4K

Quantization options

How DeepSeek R1 671B (671B params) fits at each quantization level on AMD Instinct MI350X 288GB (288.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	261.7 GB	Low	F0
Q3_K_S	3	328.8 GB	Low	F0
NVFP4	4	375.8 GB	Medium	F0
Q4_K_M	4	409.3 GB	Medium	F0
Q5_K_M	5	483.1 GB	High	F0
Q6_K	6	550.2 GB	High	F0
Q8_0	8	718.0 GB	Very High	F0
F16	16	1375.6 GB	Maximum	F0

Frequently asked questions

Can AMD Instinct MI350X 288GB run DeepSeek R1 671B?

No, DeepSeek R1 671B requires more memory than AMD Instinct MI350X 288GB provides.

How much VRAM does DeepSeek R1 671B need?

DeepSeek R1 671B (671B parameters) requires approximately 498.6 GB of memory with Q4_K_M quantization.

What is the best quantization for DeepSeek R1 671B?

The recommended quantization for DeepSeek R1 671B is Q4_K_M, which balances quality and memory efficiency.

What speed will DeepSeek R1 671B run at on AMD Instinct MI350X 288GB?

On AMD Instinct MI350X 288GB, DeepSeek R1 671B achieves approximately 9.8 tokens per second decode speed with a time-to-first-token of 19765ms using Q4_K_M quantization.

Can AMD Instinct MI350X 288GB run DeepSeek R1 671B for coding?

For coding workloads, DeepSeek R1 671B on AMD Instinct MI350X 288GB receives a F grade with 9.8 tok/s and 4K context.

What context window can DeepSeek R1 671B use on AMD Instinct MI350X 288GB?

On AMD Instinct MI350X 288GB, DeepSeek R1 671B can safely use up to 4K tokens of context. The model's official context limit is 131K, but available memory constrains the safe maximum.

What should I upgrade first if DeepSeek R1 671B feels slow on AMD Instinct MI350X 288GB?

Add more VRAM headroom. The first useful upgrade is more dedicated VRAM so you can fit the model without shrinking context or dropping to a much lower quant.

See all results for AMD Instinct MI350X 288GB See all hardware for DeepSeek R1 671B

Embed this result▼

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

<iframe src="https://willitrunai.com/embed/deepseek-r1-671b-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: