Can Qwen3-Coder-Next run on AMD Instinct MI250X 128GB?

YES — Runs Great

S92Excellent

Estimated from fit model

Qwen3-Coder-Next needs ~64.0 GB VRAM. AMD Instinct MI250X 128GB has 128.0 GB. With Q4_K_M quantization, expect ~169 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) — 64.0 GB, 168.6 tok/s, Runs well

64.0 GB required128.0 GB available

50% VRAM used

Fit status

Runs well

Decode

168.6 tok/s

TTFT

1149 ms

Safe context

256K

Memory

64.0 GB / 128.0 GB

Memory breakdown

Weights48.8 GB

KV Cache1.5 GB

Runtime0.9 GB

Headroom12.8 GB

See how fast it feels

See how fast it feelsQwen3-Coder-Next 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: 168.6 tok/s decode · 1.1s TTFT (warm) · 421 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	168.6 tok/s	627 ms	256K
Coding	S	Runs well	168.6 tok/s	1149 ms	256K
Agentic Coding	S	Runs well	168.6 tok/s	1671 ms	256K
Reasoning	S	Runs well	168.6 tok/s	1357 ms	256K
RAG	S	Runs well	168.6 tok/s	2088 ms	256K

Quantization options

How Qwen3-Coder-Next (80B params) fits at each quantization level on AMD Instinct MI250X 128GB (128.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	31.2 GB	Low	A81
Q3_K_S	3	39.2 GB	Low	A82
NVFP4	4	44.8 GB	Medium	A83
Q4_K_M	4	48.8 GB	Medium	A84
Q5_K_M	5	57.6 GB	High	S85
Q6_K	6	65.6 GB	High	S87
Q8_0Best for your GPU	8	85.6 GB	Very High	S88
F16	16	164.0 GB	Maximum	F0

Get started

Copy-paste commands to run Qwen3-Coder-Next on your machine.

Run

ollama run qwen3-coder-next

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
Qwen 3.5 122B A10B	122B	S	100.3 tok/s
Mistral Small 4 119B	119B	S	108.8 tok/s
GPT-OSS 120B	117B	S	38 tok/s
Command A 111B	111B	S	40.2 tok/s

Frequently asked questions

Can AMD Instinct MI250X 128GB run Qwen3-Coder-Next?

Yes, AMD Instinct MI250X 128GB can run Qwen3-Coder-Next with a S grade (Runs well). Expected decode speed: 168.6 tok/s.

How much VRAM does Qwen3-Coder-Next need?

Qwen3-Coder-Next (80B parameters) requires approximately 64.0 GB of memory with Q4_K_M quantization.

What is the best quantization for Qwen3-Coder-Next?

The recommended quantization for Qwen3-Coder-Next is Q4_K_M, which balances quality and memory efficiency.

What speed will Qwen3-Coder-Next run at on AMD Instinct MI250X 128GB?

On AMD Instinct MI250X 128GB, Qwen3-Coder-Next achieves approximately 168.6 tokens per second decode speed with a time-to-first-token of 1149ms using Q4_K_M quantization.

Can AMD Instinct MI250X 128GB run Qwen3-Coder-Next for coding?

For coding workloads, Qwen3-Coder-Next on AMD Instinct MI250X 128GB receives a S grade with 168.6 tok/s and 256K context.

What context window can Qwen3-Coder-Next use on AMD Instinct MI250X 128GB?

On AMD Instinct MI250X 128GB, Qwen3-Coder-Next can safely use up to 256K tokens of context. The model's official context limit is 256K, but available memory constrains the safe maximum.

See all results for AMD Instinct MI250X 128GB See all hardware for Qwen3-Coder-Next

Embed this result▼

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

<iframe src="https://willitrunai.com/embed/qwen-3-coder-next-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: