Can Codestral 21B Pruned i1 run on RX 7900 XT 20GB?

YES — Tight Fit

C50Usable

○Estimated from fit model

Codestral 21B Pruned i1 needs ~18.2 GB VRAM. RX 7900 XT 20GB has 20.0 GB. With Q4_K_M quantization, expect ~38 tok/s.

Runtime: llama.cppCapacity: TightBandwidth: 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) — 18.2 GB, 37.5 tok/s, Tight fit

18.2 GB required20.0 GB available

91% VRAM used

Fit status

Tight fit

Decode

37.5 tok/s

TTFT

5167 ms

Safe context

28K

Memory

18.2 GB / 20.0 GB

Memory breakdown

Weights12.8 GB

KV Cache2.5 GB

Runtime0.9 GB

Headroom2.0 GB

See how fast it feels

See how fast it feelsCodestral 21B Pruned i1 on RX 7900 XT 20GB
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: 37.5 tok/s decode · 5.2s TTFT (warm) · 94 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	C	Tight fit	37.5 tok/s	2818 ms	28K
Coding	C	Tight fit	37.5 tok/s	5167 ms	28K
Agentic Coding	C	Runs with offload (needs ~0.4 GB host RAM)	26.3 tok/s	10698 ms	28K
Reasoning	C	Tight fit	37.5 tok/s	6106 ms	28K
RAG	C	Runs with offload (needs ~0.4 GB host RAM)	26.3 tok/s	13373 ms	28K

Quantization options

How Codestral 21B Pruned i1 (21B params) fits at each quantization level on RX 7900 XT 20GB (20.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	8.2 GB	Low	C49
Q3_K_S	3	10.3 GB	Low	C50
NVFP4	4	11.8 GB	Medium	C50
Q4_K_M	4	12.8 GB	Medium	C50
Q5_K_MBest for your GPU	5	15.1 GB	High	C49
Q6_K	6	17.2 GB	High	F0
Q8_0	8	22.5 GB	Very High	F0
F16	16	43.1 GB	Maximum	F0