Can Granite Code 8B run on RX 6650 XT 8GB?

YES — With Offload

B64Good

○Estimated from fit model

Granite Code 8B needs ~8.5 GB VRAM. RX 6650 XT 8GB has 8.0 GB. With Q4_K_M quantization, expect ~19 tok/s.

Runtime: llama.cppCapacity: OffloadBandwidth: LowStack: StandardBottleneck: Host offload

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) — 8.5 GB, 20.6 tok/s, Runs with offload (needs ~0.3 GB host RAM)

8.5 GB required8.0 GB available

106% VRAM needed

0.5 GB over capacity — needs offload or smaller quantization

Fit status

Runs with offload (needs ~0.3 GB host RAM)

Decode

20.6 tok/s

TTFT

9400 ms

Safe context

Memory

8.5 GB / 8.0 GB

Offload

10%

Memory breakdown

Weights4.9 GB

KV Cache2.0 GB

Runtime0.9 GB

Headroom0.8 GB

See how fast it feels

See how fast it feelsGranite Code 8B on RX 6650 XT 8GB
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: 20.6 tok/s decode · 9.4s TTFT (warm) · 52 tok/s prefill

What limits this setup

It fits through host-memory offload, and offload is the main reason performance drops.

CPU or host-memory offload is active

About 10% of the working set spills out of accelerator memory, which usually hurts latency and sustained decode throughput.

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

Remove offload with more accelerator memory

Prioritize a GPU or unified-memory tier that fits the whole model natively. Removing offload usually helps more than small compute gains.

Buy headroom, not only minimum fit

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

Increase host RAM if you keep offloading

This setup may need roughly {ram} GB of extra host RAM just for the offloaded portion, before OS and other tools.

Performance by workload

Workload	Grade	Fit	Decode	TTFT	Context
Chat	A	Tight fit	29.3 tok/s	3609 ms	8K
Coding	B	Runs with offload	19.2 tok/s	10104 ms	8K
Agentic Coding	F	Too heavy	12.4 tok/s	22681 ms	8K
Reasoning	B	Runs with offload	19.2 tok/s	11942 ms	8K
RAG	F	Too heavy	12.4 tok/s	28351 ms	8K