Can LFM2 24B run on AMD Instinct MI250X 128GB?

YES — Runs Great

A80Great

Estimated from fit model

LFM2 24B needs ~30.8 GB VRAM. AMD Instinct MI250X 128GB has 128.0 GB. With Q4_K_M quantization, expect ~183 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) — 30.8 GB, 183.3 tok/s, Runs well

30.8 GB required128.0 GB available

24% VRAM used

Fit status

Runs well

Decode

183.3 tok/s

TTFT

1056 ms

Safe context

131K

Memory

30.8 GB / 128.0 GB

Memory breakdown

Weights14.6 GB

KV Cache2.4 GB

Runtime0.9 GB

Headroom12.8 GB

See how fast it feels

See how fast it feelsLFM2 24B on AMD Instinct MI250X 128GB
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: 183.3 tok/s decode · 1.1s TTFT (warm) · 458 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	183.3 tok/s	576 ms	131K
Coding	A	Runs well	183.3 tok/s	1056 ms	131K
Agentic Coding	A	Runs well	183.3 tok/s	1536 ms	131K
Reasoning	A	Runs well	183.3 tok/s	1248 ms	131K
RAG	A	Runs well	183.3 tok/s	1921 ms	131K

Inference speed

LFM2 24B inference speed — tokens per second by GPU & Mac

Estimated decode speed (tokens/sec) for LFM2 24B 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 LFM2 24B (24B params) fits at each quantization level on AMD Instinct MI250X 128GB (128.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	9.4 GB	Low	A72
Q3_K_S	3	11.8 GB	Low	A72
NVFP4	4	13.4 GB	Medium	A72
Q4_K_M	4	14.6 GB	Medium	A72
Q5_K_M	5	17.3 GB	High	A72
Q6_K	6	19.7 GB	High	A72
Q8_0	8	25.7 GB	Very High	A73
F16Best for your GPU	16	49.2 GB	Maximum	A77

Get started

Copy-paste commands to run LFM2 24B on your machine.

Run

ollama run lfm2

Your hardware

More models your AMD Instinct MI250X 128GB can run

Model	Params	Grade	Decode
Devstral 2 123B Instruct	123B	S	36.2 tok/s
Qwen3-Coder 30B A3B Instruct	30.5B	S	377.4 tok/s
Qwen 3.5 27B	27B	S	163.7 tok/s
Qwen 3.6 27B	27B	S	102 tok/s
Qwen 3.5 122B A10B	122B	S	100.3 tok/s

Frequently asked questions

Can AMD Instinct MI250X 128GB run LFM2 24B?

Yes, AMD Instinct MI250X 128GB can run LFM2 24B with a A grade (Runs well). Expected decode speed: 183.3 tok/s.

How much VRAM does LFM2 24B need?

LFM2 24B (24B parameters) requires approximately 30.8 GB of memory with Q4_K_M quantization.

What is the best quantization for LFM2 24B?

The recommended quantization for LFM2 24B is Q4_K_M, which balances quality and memory efficiency.

What speed will LFM2 24B run at on AMD Instinct MI250X 128GB?

On AMD Instinct MI250X 128GB, LFM2 24B achieves approximately 183.3 tokens per second decode speed with a time-to-first-token of 1056ms using Q4_K_M quantization.

Can AMD Instinct MI250X 128GB run LFM2 24B for coding?

For coding workloads, LFM2 24B on AMD Instinct MI250X 128GB receives a A grade with 183.3 tok/s and 131K context.

What context window can LFM2 24B use on AMD Instinct MI250X 128GB?

On AMD Instinct MI250X 128GB, LFM2 24B 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 MI250X 128GB See all hardware for LFM2 24B

Embed this result▼

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

<iframe src="https://willitrunai.com/embed/lfm2-24b-on-instinct-mi250x-128gb" 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

183.3 tok/s

576 ms

131K

Coding

Runs well

183.3 tok/s

1056 ms

131K

Agentic Coding

Runs well

183.3 tok/s

1536 ms

131K

Reasoning

Runs well

183.3 tok/s

1248 ms

131K

RAG

Runs well

183.3 tok/s

1921 ms

131K

LFM2 24B inference speed — tokens per second by GPU & Mac

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

Quantization options

How LFM2 24B (24B params) fits at each quantization level on AMD Instinct MI250X 128GB (128.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	9.4 GB	Low	A72
Q3_K_S	3	11.8 GB	Low	A72
NVFP4	4	13.4 GB	Medium	A72
Q4_K_M	4	14.6 GB	Medium	A72
Q5_K_M	5	17.3 GB	High	A72
Q6_K	6	19.7 GB	High	A72
Q8_0	8	25.7 GB	Very High	A73
F16Best for your GPU	16	49.2 GB	Maximum	A77

Model

Params

Grade

Decode

Capabilities

Devstral 2 123B Instruct

123B

36.2 tok/s

Qwen3-Coder 30B A3B Instruct

30.5B

377.4 tok/s

Qwen 3.5 27B

27B

163.7 tok/s

Qwen 3.6 27B

27B

102 tok/s

Qwen 3.5 122B A10B

122B

100.3 tok/s

Frequently asked questions

Can AMD Instinct MI250X 128GB run LFM2 24B?

Yes, AMD Instinct MI250X 128GB can run LFM2 24B with a A grade (Runs well). Expected decode speed: 183.3 tok/s.

How much VRAM does LFM2 24B need?

LFM2 24B (24B parameters) requires approximately 30.8 GB of memory with Q4_K_M quantization.

What is the best quantization for LFM2 24B?

The recommended quantization for LFM2 24B is Q4_K_M, which balances quality and memory efficiency.

What speed will LFM2 24B run at on AMD Instinct MI250X 128GB?

On AMD Instinct MI250X 128GB, LFM2 24B achieves approximately 183.3 tokens per second decode speed with a time-to-first-token of 1056ms using Q4_K_M quantization.

Can AMD Instinct MI250X 128GB run LFM2 24B for coding?

For coding workloads, LFM2 24B on AMD Instinct MI250X 128GB receives a A grade with 183.3 tok/s and 131K context.

What context window can LFM2 24B use on AMD Instinct MI250X 128GB?

On AMD Instinct MI250X 128GB, LFM2 24B can safely use up to 131K tokens of context. The model's official context limit is 131K, but available memory constrains the safe maximum.