Can Mistral Small 4 119B run on AMD Instinct MI300X 192GB?

YES — Runs Great

S93Excellent

○Estimated from fit model

Mistral Small 4 119B needs ~98.1 GB VRAM. AMD Instinct MI300X 192GB has 192.0 GB. With Q4_K_M quantization, expect ~180 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) — 98.1 GB, 180.2 tok/s, Runs well

98.1 GB required192.0 GB available

51% VRAM used

Fit status

Runs well

Decode

180.2 tok/s

TTFT

1074 ms

Safe context

256K

Memory

98.1 GB / 192.0 GB

Memory breakdown

Weights72.6 GB

KV Cache5.4 GB

Runtime0.9 GB

Headroom19.2 GB

See how fast it feels

See how fast it feelsMistral Small 4 119B on AMD Instinct MI300X 192GB
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: 180.2 tok/s decode · 1.1s TTFT (warm) · 451 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	180.2 tok/s	586 ms	256K
Coding	S	Runs well	180.2 tok/s	1074 ms	256K
Agentic Coding	S	Runs well	180.2 tok/s	1563 ms	256K
Reasoning	S	Runs well	180.2 tok/s	1270 ms	256K
RAG	S	Runs well	180.2 tok/s	1953 ms	256K

Quantization options

How Mistral Small 4 119B (119B params) fits at each quantization level on AMD Instinct MI300X 192GB (192.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	46.4 GB	Low	A82
Q3_K_S	3	58.3 GB	Low	A83
NVFP4	4	66.6 GB	Medium	A84
Q4_K_M	4	72.6 GB	Medium	A84
Q5_K_M	5	85.7 GB	High	S86
Q6_K	6	97.6 GB	High	S87
Q8_0Best for your GPU	8	127.3 GB	Very High	S88
F16	16	244.0 GB	Maximum	F0

Get started

Copy-paste commands to run Mistral Small 4 119B on your machine.

Run

lms load Mistral-Small-4-119B-2603 && lms server start

Your hardware

More models your AMD Instinct MI300X 192GB can run

Model	Params	Grade	Decode
👁 Mistral Devstral 2 123B Instruct	123B	S	59.9 tok/s
👁 Alibaba Qwen 3.5 122B A10B	122B	S	166.2 tok/s
👁 DeepSeek DeepSeek V4 Flash	284B	S	89.1 tok/s

Frequently asked questions

See all results for AMD Instinct MI300X 192GB See all hardware for Mistral Small 4 119B

URL: https://willitrunai.com/can-run/mistral-small-4-119b-on-instinct-mi300x-192gb

⇱ Mistral Small 4 119B on AMD Instinct MI300X 192GB? YES