RTX 5090 32GBコスパ重視32 GB VRAM (+8)1792 GB/s (+1446)
B
Raises estimated decode speed by about 489%.89.5 tok/sデコード
Raises estimated decode speed by about 489%.
Adds memory headroom for longer context windows and future model growth.
〜$1,999 MSRP
Can Codestral 22B v0.1 run on Tesla P40 24GB?
YES — Runs Great
C51Usable
Estimated from fit model
Codestral 22B v0.1 needs ~19.6 GB VRAM. Tesla P40 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) — 19.6 GB, 15.2 tok/s, Runs well
19.6 GB required24.0 GB available
82% VRAM used
Fit status
Runs well
Decode
15.2 tok/s
TTFT
12727 ms
Safe context
43K
Memory
19.6 GB / 24.0 GB
Memory breakdown
Weights13.4 GB
KV Cache2.6 GB
Runtime1.2 GB
Headroom2.4 GB
See how fast it feels
See how fast it feelsCodestral 22B v0.1 on Tesla P40 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.
Older PCIe generation
PCIe 3.0 is workable, but it compounds the penalty when you offload heavily or try to scale across multiple cards.
Best improvement path
Performance by workload
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | C | Runs well | 15.2 tok/s | 6942 ms | 43K |
| Coding | C | Runs well | 15.2 tok/s | 12727 ms | 43K |
| Agentic Coding | C | Tight fit | 15.2 tok/s | 18512 ms | 43K |
| Reasoning | C | Runs well | 15.2 tok/s | 15041 ms | 43K |
| RAG | C | Tight fit | 15.2 tok/s | 23140 ms | 43K |
Quantization options
How Codestral 22B v0.1 (22B params) fits at each quantization level on Tesla P40 24GB (24.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 8.6 GB | Low | C48 |
Q3_K_S | 3 | 10.8 GB | Low | C49 |
NVFP4 | 4 | 12.3 GB | Medium | C50 |
Q4_K_M | 4 | 13.4 GB | Medium | C50 |
Q5_K_M | 5 | 15.8 GB | High | C50 |
Q6_KBest for your GPU | 6 | 18.0 GB | High | C49 |
Q8_0 | 8 | 23.5 GB | Very High | F0 |
F16 | 16 | 45.1 GB | Maximum | F0 |
Get started
Copy-paste commands to run Codestral 22B v0.1 on your machine.
Run
lms load hf-sanctumai--codestral-22b-v0-1-gguf && lms server startアップグレードオプション
Codestral 22B v0.1を快適に動かすハードウェア
RTX 5090 32GBコスパ重視RTX PRO 4500 Blackwell 32GBコスパ最良32 GB VRAM (+8)896 GB/s (+550)
C
Raises estimated decode speed by about 269%.56.1 tok/sデコード
Raises estimated decode speed by about 269%.
Adds memory headroom for longer context windows and future model growth.
〜$2,499 MSRP
RTX 5000 Ada 32GBNVIDIAアップグレード32 GB VRAM (+8)576 GB/s (+230)
C
Raises estimated decode speed by about 126%.34.3 tok/sデコード
Raises estimated decode speed by about 126%.
Adds memory headroom for longer context windows and future model growth.
〜$4,000 MSRP
Frequently asked questions
Can Tesla P40 24GB run Codestral 22B v0.1?
Yes, Tesla P40 24GB can run Codestral 22B v0.1 with a C grade (Runs well). Expected decode speed: 15.2 tok/s.
How much VRAM does Codestral 22B v0.1 need?
Codestral 22B v0.1 (22B parameters) requires approximately 19.6 GB of memory with Q4_K_M quantization.
What is the best quantization for Codestral 22B v0.1?
The recommended quantization for Codestral 22B v0.1 is Q4_K_M, which balances quality and memory efficiency.
What speed will Codestral 22B v0.1 run at on Tesla P40 24GB?
On Tesla P40 24GB, Codestral 22B v0.1 achieves approximately 15.2 tokens per second decode speed with a time-to-first-token of 12727ms using Q4_K_M quantization.
Can Tesla P40 24GB run Codestral 22B v0.1 for coding?
For coding workloads, Codestral 22B v0.1 on Tesla P40 24GB receives a C grade with 15.2 tok/s and 43K context.
What context window can Codestral 22B v0.1 use on Tesla P40 24GB?
On Tesla P40 24GB, Codestral 22B v0.1 can safely use up to 43K 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-sanctumai--codestral-22b-v0-1-gguf-on-tesla-p40-24gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview: