Can DevStral 7B run on AMD Instinct MI350X 288GB?

YES — Runs Great

B70Good

Estimated from fit model

DevStral 7B needs ~35.9 GB VRAM. AMD Instinct MI350X 288GB has 288.0 GB. With Q4_K_M quantization, expect ~98 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) — 35.9 GB, 98.0 tok/s, Runs well

35.9 GB required288.0 GB available

12% VRAM used

Fit status

Runs well

Decode

98.0 tok/s

TTFT

1976 ms

Safe context

Memory

35.9 GB / 288.0 GB

Memory breakdown

Weights4.3 GB

KV Cache2.0 GB

Runtime0.9 GB

Headroom28.8 GB

See how fast it feels

See how fast it feelsDevStral 7B 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: 98.0 tok/s decode · 2.0s TTFT (warm) · 245 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	98.0 tok/s	1078 ms	8K
Coding	B	Runs well	98.0 tok/s	1976 ms	8K
Agentic Coding	B	Runs well	98.0 tok/s	2873 ms	8K
Reasoning	B	Runs well	98.0 tok/s	2335 ms	8K
RAG	B	Runs well	98.0 tok/s	3592 ms	8K

Inference speed

DevStral 7B inference speed — tokens per second by GPU & Mac

Estimated decode speed (tokens/sec) for DevStral 7B at Q4_K_M across popular GPUs and Apple Silicon, using the fastest local runtime per device. Fastest is RTX 5090 32GB at ~98 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	98.0	Fits
RTX 4090 24GB	24 GB	Q4_K_M	98.0	Fits
RTX 4080 Super 16GB	16 GB	Q4_K_M	98.0	Fits
RTX 3090 24GB	24 GB	Q4_K_M	98.0	Fits
RX 7900 XTX 24GB	24 GB	Q4_K_M	98.0	Fits
Mac Studio M3 Ultra 256GB	256 GB	Q4_K_M	98.0	Fits
Mac Studio M2 Ultra 128GB	128 GB	Q4_K_M	98.0	Fits
Mac Studio M1 Ultra 128GB	128 GB	Q4_K_M	98.0	Fits
RTX 4070 12GB	12 GB	Q4_K_M	95.2	Fits
MacBook Pro M4 Max 128GB	128 GB	Q4_K_M	94.4	Fits
MacBook Pro M4 Max 64GB	64 GB	Q4_K_M	94.4	Fits
MacBook Pro M3 Max 64GB	64 GB	Q4_K_M	60.4	Fits
RTX 3060 12GB	12 GB	Q4_K_M	59.8	Fits
MacBook Pro M1 Max 64GB	64 GB	Q4_K_M	55.4	Fits
MacBook Pro M4 Pro 48GB	48 GB	Q4_K_M	48.7	Fits
RTX 4060 8GB	8 GB	Q4_K_M	46.0	Offloads

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 DevStral 7B (7B params) fits at each quantization level on AMD Instinct MI350X 288GB (288.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	2.7 GB	Low	B61
Q3_K_S	3	3.4 GB	Low	B61
NVFP4	4	3.9 GB	Medium	B61
Q4_K_M	4	4.3 GB	Medium	B61
Q5_K_M	5	5.0 GB	High	B61
Q6_K	6	5.7 GB	High	B61
Q8_0	8	7.5 GB	Very High	B61
F16Best for your GPU	16	14.3 GB	Maximum	B61

Get started

Copy-paste commands to run DevStral 7B on your machine.

Run

ollama run devstral

Frequently asked questions

Can AMD Instinct MI350X 288GB run DevStral 7B?

Yes, AMD Instinct MI350X 288GB can run DevStral 7B with a B grade (Runs well). Expected decode speed: 98.0 tok/s.

How much VRAM does DevStral 7B need?

DevStral 7B (7B parameters) requires approximately 35.9 GB of memory with Q4_K_M quantization.

What is the best quantization for DevStral 7B?

The recommended quantization for DevStral 7B is Q4_K_M, which balances quality and memory efficiency.

What speed will DevStral 7B run at on AMD Instinct MI350X 288GB?

On AMD Instinct MI350X 288GB, DevStral 7B achieves approximately 98.0 tokens per second decode speed with a time-to-first-token of 1976ms using Q4_K_M quantization.

Can AMD Instinct MI350X 288GB run DevStral 7B for coding?

For coding workloads, DevStral 7B on AMD Instinct MI350X 288GB receives a B grade with 98.0 tok/s and 8K context.

What context window can DevStral 7B use on AMD Instinct MI350X 288GB?

On AMD Instinct MI350X 288GB, DevStral 7B can safely use up to 8K tokens of context. The model's official context limit is 8K, but available memory constrains the safe maximum.

See all results for AMD Instinct MI350X 288GB See all hardware for DevStral 7B

Embed this result▼

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

<iframe src="https://willitrunai.com/embed/devstral-7b-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: