Can Qwen3-Coder 30B A3B Instruct run on RX 7900 XTX 24GB?

YES — With Offload

S97Excellent

○Estimated from fit model

Qwen3-Coder 30B A3B Instruct needs ~23.4 GB VRAM. RX 7900 XTX 24GB has 24.0 GB. With Q4_K_M quantization, expect ~105 tok/s.

Runtime: llama.cppCapacity: OffloadBandwidth: 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) — 23.4 GB, 104.5 tok/s, Runs with offload

23.4 GB required24.0 GB available

98% VRAM used

Fit status

Runs with offload

Decode

104.5 tok/s

TTFT

1852 ms

Safe context

23K

Memory

23.4 GB / 24.0 GB

Memory breakdown

Weights18.6 GB

KV Cache1.5 GB

Runtime0.9 GB

Headroom2.4 GB

See how fast it feels

See how fast it feelsQwen3-Coder 30B A3B Instruct on RX 7900 XTX 24GB
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: 104.5 tok/s decode · 1.9s TTFT (warm) · 261 tok/s prefill

What limits this setup

This setup is broadly balanced for this model.

Very little memory headroom

You can run the model, but there is not much room left for longer context, bigger batches, extra apps, or future model updates.

Best improvement path

Buy headroom, not only minimum fit

A slightly larger memory tier gives you safer context growth and makes the recommendation more future-proof.

Performance by workload

Workload	Grade	Fit	Decode	TTFT	Context
Chat	S	Tight fit	104.5 tok/s	1010 ms	23K
Coding	S	Runs with offload	104.5 tok/s	1852 ms	23K
Agentic Coding	S	Runs with offload (needs ~0.6 GB host RAM)	72.9 tok/s	3860 ms	23K
Reasoning	S	Runs with offload	104.5 tok/s	2189 ms	23K
RAG	S	Runs with offload (needs ~0.6 GB host RAM)	72.9 tok/s	4826 ms	23K

Quantization options

How Qwen3-Coder 30B A3B Instruct (30.5B params) fits at each quantization level on RX 7900 XTX 24GB (24.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	11.9 GB	Low	S93
Q3_K_S	3	14.9 GB	Low	S93
NVFP4	4	17.1 GB	Medium	S93
Q4_K_MBest for your GPU	4	18.6 GB	Medium	S92
Q5_K_M	5	22.0 GB	High	F0
Q6_K	6	25.0 GB	High	F0
Q8_0	8	32.6 GB	Very High	F0
F16	16	62.5 GB	Maximum	F0

Get started

Copy-paste commands to run Qwen3-Coder 30B A3B Instruct on your machine.

Run

ollama run qwen3-coder

Frequently asked questions

See all results for RX 7900 XTX 24GB See all hardware for Qwen3-Coder 30B A3B Instruct

URL: https://willitrunai.com/can-run/qwen-3-coder-30b-a3b-on-rx-7900-xtx-24gb

⇱ Qwen3-Coder 30B A3B Instruct on RX 7900 XTX 24GB? YES