Can Devstral Small 1.1 run on AMD Instinct MI350X 288GB?

YES — Runs Great

A85Great

Estimated from fit model

Devstral Small 1.1 needs ~46.8 GB VRAM. AMD Instinct MI350X 288GB has 288.0 GB. With Q4_K_M quantization, expect ~336 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) — 46.8 GB, 336.0 tok/s, Runs well

46.8 GB required288.0 GB available

16% VRAM used

Fit status

Runs well

Decode

336.0 tok/s

TTFT

576 ms

Safe context

131K

Memory

46.8 GB / 288.0 GB

Memory breakdown

Weights14.6 GB

KV Cache2.4 GB

Runtime0.9 GB

Headroom28.8 GB

See how fast it feels

See how fast it feelsDevstral Small 1.1 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: 336.0 tok/s decode · 576ms TTFT (warm) · 840 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	A	Runs well	336.0 tok/s	350 ms	131K
Coding	A	Runs well	336.0 tok/s	576 ms	131K
Agentic Coding	S	Runs well	336.0 tok/s	838 ms	131K
Reasoning	A	Runs well	336.0 tok/s	681 ms	131K
RAG	S	Runs well	336.0 tok/s	1048 ms	131K

Inference speed

Devstral Small 1.1 inference speed — tokens per second by GPU & Mac

Estimated decode speed (tokens/sec) for Devstral Small 1.1 at Q4_K_M across popular GPUs and Apple Silicon, using the fastest local runtime per device. Fastest is RTX 5090 32GB at ~88 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	88.2	Fits
RTX 4090 24GB	24 GB	Q4_K_M	56.3	Tight
RX 7900 XTX 24GB	24 GB	Q4_K_M	50.8	Tight
RTX 3090 24GB	24 GB	Q4_K_M	48.1	Tight
Mac Studio M3 Ultra 256GB	256 GB	Q4_K_M	40.9	Fits
MacBook Pro M4 Max 128GB	128 GB	Q4_K_M	36.8	Fits
MacBook Pro M4 Max 64GB	64 GB	Q4_K_M	36.8	Fits
Mac Studio M2 Ultra 128GB	128 GB	Q4_K_M	34.1	Fits
Mac Studio M1 Ultra 128GB	128 GB	Q4_K_M	32.3	Fits
MacBook Pro M4 Pro 48GB	48 GB	Q4_K_M	23.2	Fits
RTX 4080 Super 16GB	16 GB	Q4_K_M	21.3	Too big
MacBook Pro M3 Max 64GB	64 GB	Q4_K_M	17.6	Fits
MacBook Pro M1 Max 64GB	64 GB	Q4_K_M	16.2	Fits
RTX 4070 12GB	12 GB	Q4_K_M	7.5	Too big
RTX 3060 12GB	12 GB	Q4_K_M	4.7	Too big
RTX 4060 8GB	8 GB	Q4_K_M	2.2	Too big

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 Small 1.1 (24B params) fits at each quantization level on AMD Instinct MI350X 288GB (288.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	9.4 GB	Low	A75
Q3_K_S	3	11.8 GB	Low	A76
NVFP4	4	13.4 GB	Medium	A76
Q4_K_M	4	14.6 GB	Medium	A76
Q5_K_M	5	17.3 GB	High	A76
Q6_K	6	19.7 GB	High	A76
Q8_0	8	25.7 GB	Very High	A77
F16Best for your GPU	16	49.2 GB	Maximum	A78

Get started

Copy-paste commands to run Devstral Small 1.1 on your machine.

Run

lms load Devstral-Small-2507 && lms server start

Your hardware

More models your AMD Instinct MI350X 288GB can run

Model	Params	Grade	Decode
Qwen 3.5 397B A17B	397B	S	78.9 tok/s
Devstral 2 123B Instruct	123B	S	84.6 tok/s
Qwen3-Coder 30B A3B Instruct	30.5B	S	883.1 tok/s
Qwen 3.5 27B	27B	S	378 tok/s
Qwen 3.6 27B	27B	S	238.7 tok/s

Frequently asked questions

Can AMD Instinct MI350X 288GB run Devstral Small 1.1?

Yes, AMD Instinct MI350X 288GB can run Devstral Small 1.1 with a A grade (Runs well). Expected decode speed: 336.0 tok/s.

How much VRAM does Devstral Small 1.1 need?

Devstral Small 1.1 (24B parameters) requires approximately 46.8 GB of memory with Q4_K_M quantization.

What is the best quantization for Devstral Small 1.1?

The recommended quantization for Devstral Small 1.1 is Q4_K_M, which balances quality and memory efficiency.

What speed will Devstral Small 1.1 run at on AMD Instinct MI350X 288GB?

On AMD Instinct MI350X 288GB, Devstral Small 1.1 achieves approximately 336.0 tokens per second decode speed with a time-to-first-token of 576ms using Q4_K_M quantization.

Can AMD Instinct MI350X 288GB run Devstral Small 1.1 for coding?

For coding workloads, Devstral Small 1.1 on AMD Instinct MI350X 288GB receives a A grade with 336.0 tok/s and 131K context.

What context window can Devstral Small 1.1 use on AMD Instinct MI350X 288GB?

On AMD Instinct MI350X 288GB, Devstral Small 1.1 can safely use up to 131K tokens of context. The model's official context limit is 131K, but available memory constrains the safe maximum.

See all results for AMD Instinct MI350X 288GB See all hardware for Devstral Small 1.1

Embed this result▼

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

<iframe src="https://willitrunai.com/embed/devstral-small-2507-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: