Can DeepSeek LLM 67B run on AMD Instinct MI350X 288GB?

YES — Runs Great

B57Good

Estimated from fit model

DeepSeek LLM 67B needs ~76.4 GB VRAM. AMD Instinct MI350X 288GB has 288.0 GB. With Q4_K_M quantization, expect ~155 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) — 76.4 GB, 155.4 tok/s, Runs well

76.4 GB required288.0 GB available

27% VRAM used

Fit status

Runs well

Decode

155.4 tok/s

TTFT

1246 ms

Safe context

Memory

76.4 GB / 288.0 GB

Memory breakdown

Weights40.9 GB

KV Cache5.8 GB

Runtime0.9 GB

Headroom28.8 GB

See how fast it feels

See how fast it feelsDeepSeek LLM 67B 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: 155.4 tok/s decode · 1.2s TTFT (warm) · 389 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	155.4 tok/s	680 ms	4K
Coding	B	Runs well	155.4 tok/s	1246 ms	4K
Agentic Coding	B	Runs well	155.4 tok/s	1812 ms	4K
Reasoning	B	Runs well	155.4 tok/s	1472 ms	4K
RAG	B	Runs well	155.4 tok/s	2265 ms	4K

Quantization options

How DeepSeek LLM 67B (67B params) fits at each quantization level on AMD Instinct MI350X 288GB (288.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	26.1 GB	Low	C47
Q3_K_S	3	32.8 GB	Low	C48
NVFP4	4	37.5 GB	Medium	C48
Q4_K_M	4	40.9 GB	Medium	C48
Q5_K_M	5	48.2 GB	High	C49
Q6_K	6	54.9 GB	High	C49
Q8_0	8	71.7 GB	Very High	C50
F16Best for your GPU	16	137.4 GB	Maximum	B55

Get started

Copy-paste commands to run DeepSeek LLM 67B on your machine.

Run

docker run --rm -it ghcr.io/ggerganov/llama.cpp:full \
  --hf-repo "deepseek-ai/deepseek-llm-67b-chat" \
  --hf-file "deepseek-llm-67b-chat-Q4_K_M.gguf" \
  -c 4096 -ngl 99

Frequently asked questions

Can AMD Instinct MI350X 288GB run DeepSeek LLM 67B?

Yes, AMD Instinct MI350X 288GB can run DeepSeek LLM 67B with a B grade (Runs well). Expected decode speed: 155.4 tok/s.

How much VRAM does DeepSeek LLM 67B need?

DeepSeek LLM 67B (67B parameters) requires approximately 76.4 GB of memory with Q4_K_M quantization.

What is the best quantization for DeepSeek LLM 67B?

The recommended quantization for DeepSeek LLM 67B is Q4_K_M, which balances quality and memory efficiency.

What speed will DeepSeek LLM 67B run at on AMD Instinct MI350X 288GB?

On AMD Instinct MI350X 288GB, DeepSeek LLM 67B achieves approximately 155.4 tokens per second decode speed with a time-to-first-token of 1246ms using Q4_K_M quantization.

Can AMD Instinct MI350X 288GB run DeepSeek LLM 67B for coding?

For coding workloads, DeepSeek LLM 67B on AMD Instinct MI350X 288GB receives a B grade with 155.4 tok/s and 4K context.

What context window can DeepSeek LLM 67B use on AMD Instinct MI350X 288GB?

On AMD Instinct MI350X 288GB, DeepSeek LLM 67B can safely use up to 4K tokens of context. The model's official context limit is 4K, but available memory constrains the safe maximum.

See all results for AMD Instinct MI350X 288GB See all hardware for DeepSeek LLM 67B

Embed this result▼

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

<iframe src="https://willitrunai.com/embed/deepseek-llm-67b-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:

Workload

Grade

Fit

Decode

TTFT

Context

Chat

Runs well

155.4 tok/s

680 ms

Coding

Runs well

155.4 tok/s

1246 ms

Agentic Coding

Runs well

155.4 tok/s

1812 ms

Reasoning

Runs well

155.4 tok/s

1472 ms

RAG

Runs well

155.4 tok/s

2265 ms

Quantization options

How DeepSeek LLM 67B (67B params) fits at each quantization level on AMD Instinct MI350X 288GB (288.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	26.1 GB	Low	C47
Q3_K_S	3	32.8 GB	Low	C48
NVFP4	4	37.5 GB	Medium	C48
Q4_K_M	4	40.9 GB	Medium	C48
Q5_K_M	5	48.2 GB	High	C49
Q6_K	6	54.9 GB	High	C49
Q8_0	8	71.7 GB	Very High	C50
F16Best for your GPU	16	137.4 GB	Maximum	B55

Frequently asked questions

Can AMD Instinct MI350X 288GB run DeepSeek LLM 67B?

Yes, AMD Instinct MI350X 288GB can run DeepSeek LLM 67B with a B grade (Runs well). Expected decode speed: 155.4 tok/s.

How much VRAM does DeepSeek LLM 67B need?

DeepSeek LLM 67B (67B parameters) requires approximately 76.4 GB of memory with Q4_K_M quantization.

What is the best quantization for DeepSeek LLM 67B?

The recommended quantization for DeepSeek LLM 67B is Q4_K_M, which balances quality and memory efficiency.

What speed will DeepSeek LLM 67B run at on AMD Instinct MI350X 288GB?

On AMD Instinct MI350X 288GB, DeepSeek LLM 67B achieves approximately 155.4 tokens per second decode speed with a time-to-first-token of 1246ms using Q4_K_M quantization.

Can AMD Instinct MI350X 288GB run DeepSeek LLM 67B for coding?

For coding workloads, DeepSeek LLM 67B on AMD Instinct MI350X 288GB receives a B grade with 155.4 tok/s and 4K context.

What context window can DeepSeek LLM 67B use on AMD Instinct MI350X 288GB?

On AMD Instinct MI350X 288GB, DeepSeek LLM 67B can safely use up to 4K tokens of context. The model's official context limit is 4K, but available memory constrains the safe maximum.