Can Codestral 2 25.08 run on AMD Instinct MI300A 128GB?

YES — Runs Great

A81Great

○Estimated from fit model

Codestral 2 25.08 needs ~29.6 GB VRAM. AMD Instinct MI300A 128GB has 128.0 GB. With Q4_K_M quantization, expect ~279 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) — 29.6 GB, 279.4 tok/s, Runs well

29.6 GB required128.0 GB available

23% VRAM used

Fit status

Runs well

Decode

279.4 tok/s

TTFT

693 ms

Safe context

256K

Memory

29.6 GB / 128.0 GB

Memory breakdown

Weights13.4 GB

KV Cache2.4 GB

Runtime0.9 GB

Headroom12.8 GB

See how fast it feels

See how fast it feelsCodestral 2 25.08 on AMD Instinct MI300A 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: 279.4 tok/s decode · 693ms TTFT (warm) · 698 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	279.4 tok/s	378 ms	256K
Coding	A	Runs well	279.4 tok/s	693 ms	256K
Agentic Coding	A	Runs well	279.4 tok/s	1008 ms	256K
Reasoning	A	Runs well	279.4 tok/s	819 ms	256K
RAG	A	Runs well	279.4 tok/s	1260 ms	256K

Quantization options

How Codestral 2 25.08 (22B params) fits at each quantization level on AMD Instinct MI300A 128GB (128.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	8.6 GB	Low	A73
Q3_K_S	3	10.8 GB	Low	A73
NVFP4	4	12.3 GB	Medium	A73
Q4_K_M	4	13.4 GB	Medium	A73
Q5_K_M	5	15.8 GB	High	A73
Q6_K	6	18.0 GB	High	A73
Q8_0	8	23.5 GB	Very High	A74
F16Best for your GPU	16	45.1 GB	Maximum	A77

Get started

Copy-paste commands to run Codestral 2 25.08 on your machine.

Run

lms load codestral-2508 && lms server start

Your hardware

More models your AMD Instinct MI300A 128GB can run

Model	Params	Grade	Decode
👁 Mistral Devstral 2 123B Instruct	123B	S	53.8 tok/s
👁 Alibaba Qwen3-Coder 30B A3B Instruct	30.5B	S	561 tok/s
👁 Alibaba Qwen 3.5 27B	27B	S	243.3 tok/s
👁 Alibaba Qwen 3.6 27B	27B	S	151.7 tok/s
👁 Alibaba Qwen 3.5 122B A10B	122B	S	149.2 tok/s

Frequently asked questions

See all results for AMD Instinct MI300A 128GB See all hardware for Codestral 2 25.08

URL: https://willitrunai.com/can-run/codestral-2-25.08-on-instinct-mi300a-128gb

⇱ Codestral 2 25.08 on AMD Instinct MI300A 128GB? YES