RTX 5090 32GB经济之选32 GB VRAM (+8)1792 GB/s (+1492)
C
Raises estimated decode speed by about 516%.93.7 tok/s 解码
Raises estimated decode speed by about 516%.
Adds memory headroom for longer context windows and future model growth.
~$1,999 MSRP
Can Codestral 21B Pruned i1 run on NVIDIA L4 24GB?
YES — Runs Great
C51Usable
Estimated from fit model
Codestral 21B Pruned i1 needs ~18.9 GB VRAM. NVIDIA L4 24GB has 24.0 GB. With Q4_K_M quantization, expect ~15 tok/s.
Runtime: OllamaCapacity: RoomyBandwidth: LowStack: 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) — 18.9 GB, 15.2 tok/s, Runs well
18.9 GB required24.0 GB available
79% VRAM used
Fit status
Runs well
Decode
15.2 tok/s
TTFT
12718 ms
Safe context
49K
Memory
18.9 GB / 24.0 GB
Memory breakdown
Weights12.8 GB
KV Cache2.5 GB
Runtime1.2 GB
Headroom2.4 GB
See how fast it feels
See how fast it feelsCodestral 21B Pruned i1 on NVIDIA L4 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: 15.2 tok/s decode · 12.7s TTFT (warm) · 38 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 | Runs well | 15.2 tok/s | 6937 ms | 49K |
| Coding | C | Runs well | 15.2 tok/s | 12718 ms | 49K |
| Agentic Coding | C | Tight fit | 15.2 tok/s | 18499 ms | 49K |
| Reasoning | C | Runs well | 15.2 tok/s | 15030 ms | 49K |
| RAG | C | Tight fit | 15.2 tok/s | 23124 ms | 49K |
Quantization options
How Codestral 21B Pruned i1 (21B params) fits at each quantization level on NVIDIA L4 24GB (24.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 8.2 GB | Low | C47 |
Q3_K_S | 3 | 10.3 GB | Low | C49 |
NVFP4 | 4 | 11.8 GB | Medium | C50 |
Q4_K_M | 4 | 12.8 GB | Medium | C50 |
Q5_K_M | 5 | 15.1 GB | High | C49 |
Q6_KBest for your GPU | 6 | 17.2 GB | High | C49 |
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 start升级选项
能流畅运行 Codestral 21B Pruned i1 的硬件
RTX 5090 32GB经济之选RTX PRO 4500 Blackwell 32GB最佳性价比32 GB VRAM (+8)896 GB/s (+596)
C
Raises estimated decode speed by about 287%.58.8 tok/s 解码
Raises estimated decode speed by about 287%.
Adds memory headroom for longer context windows and future model growth.
~$2,499 MSRP
RTX 5000 Ada 32GBNVIDIA 升级32 GB VRAM (+8)576 GB/s (+276)
C
Raises estimated decode speed by about 137%.36 tok/s 解码
Raises estimated decode speed by about 137%.
Adds memory headroom for longer context windows and future model growth.
~$4,000 MSRP
Frequently asked questions
Can NVIDIA L4 24GB run Codestral 21B Pruned i1?
Yes, NVIDIA L4 24GB can run Codestral 21B Pruned i1 with a C grade (Runs well). Expected decode speed: 15.2 tok/s.
How much VRAM does Codestral 21B Pruned i1 need?
Codestral 21B Pruned i1 (21B parameters) requires approximately 18.9 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 NVIDIA L4 24GB?
On NVIDIA L4 24GB, Codestral 21B Pruned i1 achieves approximately 15.2 tokens per second decode speed with a time-to-first-token of 12718ms using Q4_K_M quantization.
Can NVIDIA L4 24GB run Codestral 21B Pruned i1 for coding?
For coding workloads, Codestral 21B Pruned i1 on NVIDIA L4 24GB receives a C grade with 15.2 tok/s and 49K context.
What context window can Codestral 21B Pruned i1 use on NVIDIA L4 24GB?
On NVIDIA L4 24GB, Codestral 21B Pruned i1 can safely use up to 49K tokens of context. The model's official context limit is —, but available memory constrains the safe maximum.
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-l4-24gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview: