Can DeepSeek V4 Flash run on AMD Instinct MI350X 288GB?

YES — Runs Great

S98Excellent

Estimated from fit model

DeepSeek V4 Flash needs ~190.1 GB VRAM. AMD Instinct MI350X 288GB has 288.0 GB. With NVFP4 quantization, expect ~115 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

NVFP4 (Medium quality) — 189.0 GB, 125.8 tok/s, Runs well

189.0 GB required288.0 GB available

66% VRAM used

Fit status

Runs well

Decode

125.8 tok/s

TTFT

1539 ms

Safe context

1.0M

Memory

189.0 GB / 288.0 GB

Memory breakdown

Weights158.0 GB

KV Cache1.3 GB

Runtime0.9 GB

Headroom28.8 GB

See how fast it feels

See how fast it feelsDeepSeek V4 Flash 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: 125.8 tok/s decode · 1.5s TTFT (warm) · 315 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	S	Runs well	114.5 tok/s	922 ms	1.0M
Coding	S	Runs well	114.5 tok/s	1690 ms	1.0M
Agentic Coding	S	Runs well	114.5 tok/s	2459 ms	1.0M
Reasoning	S	Runs well	114.5 tok/s	1998 ms	1.0M
RAG	S	Runs well	114.5 tok/s	3073 ms	1.0M

Inference speed

DeepSeek V4 Flash inference speed — tokens per second by GPU & Mac

Estimated decode speed (tokens/sec) for DeepSeek V4 Flash at NVFP4 across popular GPUs and Apple Silicon, including multi-GPU rigs, using the fastest local runtime per device. Fastest is Mac Studio M3 Ultra 256GB at ~18 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?
Mac Studio M3 Ultra 256GB	256 GB	NVFP4	17.8	Offloads
Mac Studio M2 Ultra 128GB	128 GB	NVFP4	7.0	Too big
Mac Studio M1 Ultra 128GB	128 GB	NVFP4	6.7	Too big
MacBook Pro M4 Max 128GB	128 GB	NVFP4	5.2	Too big
MacBook Pro M4 Max 64GB	64 GB	NVFP4	5.2	Too big
RTX 5090 32GB	32 GB	NVFP4	3.9	Too big
2× RX 7900 XTX 24GB	48 GB	NVFP4	3.8	Too big
MacBook Pro M3 Max 64GB	64 GB	NVFP4	3.6	Too big
MacBook Pro M1 Max 64GB	64 GB	NVFP4	3.3	Too big
MacBook Pro M4 Pro 48GB	48 GB	NVFP4	3.2	Too big
2× RTX 4090 24GB	48 GB	NVFP4	2.6	Too big
RTX 4090 24GB	24 GB	NVFP4	2.5	Too big
2× RTX 3090 24GB	48 GB	NVFP4	2.3	Too big
RX 7900 XTX 24GB	24 GB	NVFP4	2.2	Too big
RTX 3090 24GB	24 GB	NVFP4	2.1	Too big
RTX 4080 Super 16GB	16 GB	NVFP4	2.0	Too big
RTX 4070 12GB	12 GB	NVFP4	2.0	Too big
RTX 3060 12GB	12 GB	NVFP4	2.0	Too big
RTX 4060 8GB	8 GB	NVFP4	2.0	Too big
4× RTX 3060 12GB	48 GB	NVFP4	2.0	Too big

Estimates for single-stream decoding at NVFP4; 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 V4 Flash (284B params) fits at each quantization level on AMD Instinct MI350X 288GB (288.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	110.8 GB	Low	S87
Q3_K_S	3	139.2 GB	Low	S89
NVFP4	4	159.0 GB	Medium	S90
Q4_K_M	4	173.2 GB	Medium	S90
Q5_K_M	5	204.5 GB	High	S90
Q6_KBest for your GPU	6	232.9 GB	High	S90
Q8_0	8	303.9 GB	Very High	F0
F16	16	582.2 GB	Maximum	F0

Get started

Copy-paste commands to run DeepSeek V4 Flash on your machine.

Run

docker run --rm -it ghcr.io/ggerganov/llama.cpp:full \
  --hf-repo "deepseek-ai/DeepSeek-V4-Flash" \
  --hf-file "DeepSeek-V4-Flash-NVFP4.gguf" \
  -c 4096 -ngl 99

Your hardware

More models your AMD Instinct MI350X 288GB can run

Model	Params	Grade	Decode	Capabilities
Qwen 3.5 397B A17B	397B	S	78.9 tok/s

Frequently asked questions

Can AMD Instinct MI350X 288GB run DeepSeek V4 Flash?

Yes, AMD Instinct MI350X 288GB can run DeepSeek V4 Flash with a S grade (Runs well). Expected decode speed: 114.5 tok/s.

How much VRAM does DeepSeek V4 Flash need?

DeepSeek V4 Flash (284B parameters) requires approximately 190.1 GB of memory with NVFP4 quantization.

What is the best quantization for DeepSeek V4 Flash?

The recommended quantization for DeepSeek V4 Flash is NVFP4, which balances quality and memory efficiency.

What speed will DeepSeek V4 Flash run at on AMD Instinct MI350X 288GB?

On AMD Instinct MI350X 288GB, DeepSeek V4 Flash achieves approximately 114.5 tokens per second decode speed with a time-to-first-token of 1690ms using NVFP4 quantization.

Can AMD Instinct MI350X 288GB run DeepSeek V4 Flash for coding?

For coding workloads, DeepSeek V4 Flash on AMD Instinct MI350X 288GB receives a S grade with 114.5 tok/s and 1.0M context.

What context window can DeepSeek V4 Flash use on AMD Instinct MI350X 288GB?

On AMD Instinct MI350X 288GB, DeepSeek V4 Flash can safely use up to 1.0M tokens of context. The model's official context limit is 1.0M, but available memory constrains the safe maximum.

See all results for AMD Instinct MI350X 288GB See all hardware for DeepSeek V4 Flash

Embed this result▼

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

<iframe src="https://willitrunai.com/embed/deepseek-v4-flash-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

114.5 tok/s

922 ms

1.0M

Coding

Runs well

114.5 tok/s

1690 ms

1.0M

Agentic Coding

Runs well

114.5 tok/s

2459 ms

1.0M

Reasoning

Runs well

114.5 tok/s

1998 ms

1.0M

RAG

Runs well

114.5 tok/s

3073 ms

1.0M

DeepSeek V4 Flash inference speed — tokens per second by GPU & Mac

GPU / Mac

Memory

Quant

Speed (tok/s)

Fits?

Mac Studio M3 Ultra 256GB

256 GB

NVFP4

17.8

Offloads

Mac Studio M2 Ultra 128GB

128 GB

NVFP4

7.0

Too big

Mac Studio M1 Ultra 128GB

128 GB

NVFP4

6.7

Too big

MacBook Pro M4 Max 128GB

128 GB

NVFP4

5.2

Too big

MacBook Pro M4 Max 64GB

64 GB

NVFP4

5.2

Too big

RTX 5090 32GB

32 GB

NVFP4

3.9

Too big

2× RX 7900 XTX 24GB

48 GB

NVFP4

3.8

Too big

MacBook Pro M3 Max 64GB

64 GB

NVFP4

3.6

Too big

MacBook Pro M1 Max 64GB

64 GB

NVFP4

3.3

Too big

MacBook Pro M4 Pro 48GB

48 GB

NVFP4

3.2

Too big

2× RTX 4090 24GB

48 GB

NVFP4

2.6

Too big

RTX 4090 24GB

24 GB

NVFP4

2.5

Too big

2× RTX 3090 24GB

48 GB

NVFP4

2.3

Too big

RX 7900 XTX 24GB

24 GB

NVFP4

2.2

Too big

RTX 3090 24GB

24 GB

NVFP4

2.1

Too big

RTX 4080 Super 16GB

16 GB

NVFP4

2.0

Too big

RTX 4070 12GB

12 GB

NVFP4

2.0

Too big

RTX 3060 12GB

12 GB

NVFP4

2.0

Too big

RTX 4060 8GB

8 GB

NVFP4

2.0

Too big

4× RTX 3060 12GB

48 GB

NVFP4

2.0

Too big

Quantization options

How DeepSeek V4 Flash (284B params) fits at each quantization level on AMD Instinct MI350X 288GB (288.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	110.8 GB	Low	S87
Q3_K_S	3	139.2 GB	Low	S89
NVFP4	4	159.0 GB	Medium	S90
Q4_K_M	4	173.2 GB	Medium	S90
Q5_K_M	5	204.5 GB	High	S90
Q6_KBest for your GPU	6	232.9 GB	High	S90
Q8_0	8	303.9 GB	Very High	F0
F16	16	582.2 GB	Maximum	F0

Model

Params

Grade

Decode

Capabilities

Qwen 3.5 397B A17B

397B

78.9 tok/s

Frequently asked questions

Can AMD Instinct MI350X 288GB run DeepSeek V4 Flash?

Yes, AMD Instinct MI350X 288GB can run DeepSeek V4 Flash with a S grade (Runs well). Expected decode speed: 114.5 tok/s.

How much VRAM does DeepSeek V4 Flash need?

DeepSeek V4 Flash (284B parameters) requires approximately 190.1 GB of memory with NVFP4 quantization.

What is the best quantization for DeepSeek V4 Flash?

The recommended quantization for DeepSeek V4 Flash is NVFP4, which balances quality and memory efficiency.

What speed will DeepSeek V4 Flash run at on AMD Instinct MI350X 288GB?

On AMD Instinct MI350X 288GB, DeepSeek V4 Flash achieves approximately 114.5 tokens per second decode speed with a time-to-first-token of 1690ms using NVFP4 quantization.

Can AMD Instinct MI350X 288GB run DeepSeek V4 Flash for coding?

For coding workloads, DeepSeek V4 Flash on AMD Instinct MI350X 288GB receives a S grade with 114.5 tok/s and 1.0M context.

What context window can DeepSeek V4 Flash use on AMD Instinct MI350X 288GB?

On AMD Instinct MI350X 288GB, DeepSeek V4 Flash can safely use up to 1.0M tokens of context. The model's official context limit is 1.0M, but available memory constrains the safe maximum.