RTX 3090 24GBGünstige Wahl24 GB VRAM (+4)936 GB/s (+296)
C
Raises estimated decode speed by about 31%.51.1 tok/s Dekodierung
Raises estimated decode speed by about 31%.
ca. $1,499 MSRP
Can Codestral 21B Pruned i1 run on RTX A4500 20GB?
YES — Tight Fit
C51Usable
Estimated from fit model
Codestral 21B Pruned i1 needs ~18.5 GB VRAM. RTX A4500 20GB has 20.0 GB. With Q4_K_M quantization, expect ~39 tok/s.
Runtime: OllamaCapacity: TightBandwidth: MediumStack: BasicBottleneck: 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.
Select quantization to explore
Q4_K_M (Medium quality) — 18.5 GB, 39.0 tok/s, Tight fit
18.5 GB required20.0 GB available
93% VRAM used
Fit status
Tight fit
Decode
39.0 tok/s
TTFT
4968 ms
Safe context
26K
Memory
18.5 GB / 20.0 GB
Memory breakdown
Weights12.8 GB
KV Cache2.5 GB
Runtime1.2 GB
Headroom2.0 GB
See how fast it feels
See how fast it feelsCodestral 21B Pruned i1 on RTX A4500 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: 39.0 tok/s decode · 5.0s TTFT (warm) · 97 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 | C | Tight fit | 39.0 tok/s | 2710 ms | 26K |
| Coding | C | Tight fit | 39.0 tok/s | 4968 ms | 26K |
| Agentic Coding | C | Runs with offload (needs ~0.6 GB host RAM) | 26.6 tok/s | 10604 ms | 26K |
| Reasoning | C | Tight fit | 39.0 tok/s | 5871 ms | 26K |
| RAG | C | Runs with offload (needs ~0.6 GB host RAM) | 26.6 tok/s | 13255 ms | 26K |
Quantization options
How Codestral 21B Pruned i1 (21B params) fits at each quantization level on RTX A4500 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 |
Get started
Copy-paste commands to run Codestral 21B Pruned i1 on your machine.
Run
lms load hf-mradermacher--codestral-21b-pruned-i1-gguf && lms server startUpgrade-Optionen
Hardware, die Codestral 21B Pruned i1 gut ausführt
RTX 3090 24GBGünstige WahlRTX 4090 24GBBestes Preis-Leistungs-Verhältnis24 GB VRAM (+4)1008 GB/s (+368)
B
Raises estimated decode speed by about 53%.59.8 tok/s Dekodierung
Raises estimated decode speed by about 53%.
ca. $1,599 MSRP
RTX A5500 24GBNVIDIA-Upgrade24 GB VRAM (+4)768 GB/s (+128)
C
This setup is broadly balanced for this model.46.8 tok/s Dekodierung
ca. $3,200 MSRP
Frequently asked questions
Can RTX A4500 20GB run Codestral 21B Pruned i1?
Yes, RTX A4500 20GB can run Codestral 21B Pruned i1 with a C grade (Tight fit). Expected decode speed: 39.0 tok/s.
How much VRAM does Codestral 21B Pruned i1 need?
Codestral 21B Pruned i1 (21B parameters) requires approximately 18.5 GB of memory with Q4_K_M quantization.
What is the best quantization for Codestral 21B Pruned i1?
The recommended quantization for Codestral 21B Pruned i1 is Q4_K_M, which balances quality and memory efficiency.
What speed will Codestral 21B Pruned i1 run at on RTX A4500 20GB?
On RTX A4500 20GB, Codestral 21B Pruned i1 achieves approximately 39.0 tokens per second decode speed with a time-to-first-token of 4968ms using Q4_K_M quantization.
Can RTX A4500 20GB run Codestral 21B Pruned i1 for coding?
For coding workloads, Codestral 21B Pruned i1 on RTX A4500 20GB receives a C grade with 39.0 tok/s and 26K context.
What context window can Codestral 21B Pruned i1 use on RTX A4500 20GB?
On RTX A4500 20GB, Codestral 21B Pruned i1 can safely use up to 26K tokens of context. The model's official context limit is —, but available memory constrains the safe maximum.
What should I upgrade first if Codestral 21B Pruned i1 feels slow on RTX A4500 20GB?
Buy headroom, not only minimum fit. A slightly larger memory tier gives you safer context growth and makes the recommendation more future-proof.
Embed this result▼
Paste this snippet into any page to show a live fit card.
<iframe src="https://willitrunai.com/embed/hf-mradermacher--codestral-21b-pruned-i1-gguf-on-rtx-a4500-20gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview: