Can DeepSeek R1 1.5B run on AMD Instinct MI350X 288GB?

YES — Runs Great

C50Usable

Estimated from fit model

DeepSeek R1 1.5B needs ~31.0 GB VRAM. AMD Instinct MI350X 288GB has 288.0 GB. With Q4_K_M quantization, expect ~21 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) — 31.0 GB, 21.0 tok/s, Runs well

31.0 GB required288.0 GB available

11% VRAM used

Fit status

Runs well

Decode

21.0 tok/s

TTFT

9219 ms

Safe context

33K

Memory

31.0 GB / 288.0 GB

Memory breakdown

Weights0.9 GB

KV Cache0.4 GB

Runtime0.9 GB

Headroom28.8 GB

See how fast it feels

See how fast it feelsDeepSeek R1 1.5B on AMD Instinct MI350X 288GB
1st promptCold start — includes initialization
>Write a Python function to sort a list
Here's a Python function that sorts a list using quicksort:

def quicksort(arr):
    if len(arr) <= 1:
        return arr
    pivot = arr[len(arr) // 2]
    left   = [x for x in arr if x < pivot]
    middle = [x for x in arr if x == pivot]
    right  = [x for x in arr if x > pivot]
    return quicksort(left) + middle + quicksort(right)

# Example usage
numbers = [3, 6, 8, 10, 1, 2, 1]
print(quicksort(numbers))  # [1, 1, 2, 3, 6, 8, 10]

The algorithm picks a pivot, partitions the list into smaller, equal, and larger elements, then recursively sorts each partition and concatenates the results.
2nd promptWarm — model ready, no init overhead
>Now add type hints and a docstring
def quicksort(arr: list[int]) -> list[int]:
    """Sort a list using the quicksort algorithm.

    Args:
        arr: List of integers to sort.

    Returns:
        A new sorted list.
    """
    if len(arr) <= 1:
        return arr
    pivot = arr[len(arr) // 2]
    left   = [x for x in arr if x < pivot]
    middle = [x for x in arr if x == pivot]
    right  = [x for x in arr if x > pivot]
    return quicksort(left) + middle + quicksort(right)

Added type hints for the input and return type, plus a Google-style docstring.
Estimated: 21.0 tok/s decode · 9.2s TTFT (warm) · 53 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	C	Runs well	21.0 tok/s	5029 ms	33K
Coding	C	Runs well	21.0 tok/s	9219 ms	33K
Agentic Coding	C	Runs well	21.0 tok/s	13410 ms	33K
Reasoning	C	Runs well	21.0 tok/s	10895 ms	33K
RAG	C	Runs well	21.0 tok/s	16762 ms	33K

Inference speed

DeepSeek R1 1.5B inference speed — tokens per second by GPU & Mac

Estimated decode speed (tokens/sec) for DeepSeek R1 1.5B at Q4_K_M across popular GPUs and Apple Silicon, using the fastest local runtime per device. Fastest is RTX 5090 32GB at ~29 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	28.5	Fits
RTX 4090 24GB	24 GB	Q4_K_M	24.0	Fits
RTX 4080 Super 16GB	16 GB	Q4_K_M	24.0	Fits
RTX 3090 24GB	24 GB	Q4_K_M	21.0	Fits
RTX 4070 12GB	12 GB	Q4_K_M	21.0	Fits
RTX 3060 12GB	12 GB	Q4_K_M	21.0	Fits
RTX 4060 8GB	8 GB	Q4_K_M	21.0	Fits
RX 7900 XTX 24GB	24 GB	Q4_K_M	21.0	Fits
MacBook Pro M4 Max 128GB	128 GB	Q4_K_M	21.0	Fits
Mac Studio M3 Ultra 256GB	256 GB	Q4_K_M	21.0	Fits
Mac Studio M2 Ultra 128GB	128 GB	Q4_K_M	21.0	Fits
Mac Studio M1 Ultra 128GB	128 GB	Q4_K_M	21.0	Fits
MacBook Pro M4 Max 64GB	64 GB	Q4_K_M	21.0	Fits
MacBook Pro M3 Max 64GB	64 GB	Q4_K_M	21.0	Fits
MacBook Pro M1 Max 64GB	64 GB	Q4_K_M	21.0	Fits
MacBook Pro M4 Pro 48GB	48 GB	Q4_K_M	21.0	Fits

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 DeepSeek R1 1.5B (1.5B params) fits at each quantization level on AMD Instinct MI350X 288GB (288.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	0.6 GB	Low	C47
Q3_K_S	3	0.7 GB	Low	C47
NVFP4	4	0.8 GB	Medium	C47
Q4_K_M	4	0.9 GB	Medium	C47
Q5_K_M	5	1.1 GB	High	C47
Q6_K	6	1.2 GB	High	C47
Q8_0	8	1.6 GB	Very High	C47
F16Best for your GPU	16	3.1 GB	Maximum	C47

Get started

Copy-paste commands to run DeepSeek R1 1.5B on your machine.

Run

ollama run deepseek-r1:1.5b

Frequently asked questions

Can AMD Instinct MI350X 288GB run DeepSeek R1 1.5B?

Yes, AMD Instinct MI350X 288GB can run DeepSeek R1 1.5B with a C grade (Runs well). Expected decode speed: 21.0 tok/s.

How much VRAM does DeepSeek R1 1.5B need?

DeepSeek R1 1.5B (1.5B parameters) requires approximately 31.0 GB of memory with Q4_K_M quantization.

What is the best quantization for DeepSeek R1 1.5B?

The recommended quantization for DeepSeek R1 1.5B is Q4_K_M, which balances quality and memory efficiency.

What speed will DeepSeek R1 1.5B run at on AMD Instinct MI350X 288GB?

On AMD Instinct MI350X 288GB, DeepSeek R1 1.5B achieves approximately 21.0 tokens per second decode speed with a time-to-first-token of 9219ms using Q4_K_M quantization.

Can AMD Instinct MI350X 288GB run DeepSeek R1 1.5B for coding?

For coding workloads, DeepSeek R1 1.5B on AMD Instinct MI350X 288GB receives a C grade with 21.0 tok/s and 33K context.

What context window can DeepSeek R1 1.5B use on AMD Instinct MI350X 288GB?

On AMD Instinct MI350X 288GB, DeepSeek R1 1.5B can safely use up to 33K tokens of context. The model's official context limit is 33K, but available memory constrains the safe maximum.

See all results for AMD Instinct MI350X 288GB See all hardware for DeepSeek R1 1.5B

Embed this result▼

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

<iframe src="https://willitrunai.com/embed/deepseek-r1-distill-qwen-1.5b-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: