RTX 3090 24GB经济之选24 GB VRAM (+4)936 GB/s (+576)
C
Raises estimated decode speed by about 133%.48.8 tok/s 解码
Raises estimated decode speed by about 133%.
~$1,499 MSRP
Can Codestral 22B v0.1 run on RTX 4000 Ada 20GB?
YES — With Offload
C49Usable
Estimated from fit model
Codestral 22B v0.1 needs ~19.2 GB VRAM. RTX 4000 Ada 20GB has 20.0 GB. With Q4_K_M quantization, expect ~21 tok/s.
Runtime: OllamaCapacity: OffloadBandwidth: 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) — 19.2 GB, 20.9 tok/s, Runs with offload
19.2 GB required20.0 GB available
96% VRAM used
Fit status
Runs with offload
Decode
20.9 tok/s
TTFT
9253 ms
Safe context
21K
Memory
19.2 GB / 20.0 GB
Memory breakdown
Weights13.4 GB
KV Cache2.6 GB
Runtime1.2 GB
Headroom2.0 GB
See how fast it feels
See how fast it feelsCodestral 22B v0.1 on RTX 4000 Ada 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: 20.9 tok/s decode · 9.3s TTFT (warm) · 52 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 | 20.9 tok/s | 5047 ms | 21K |
| Coding | C | Runs with offload | 20.9 tok/s | 9253 ms | 21K |
| Agentic Coding | D | Very compromised (needs ~1.1 GB host RAM) | 13.1 tok/s | 21464 ms | 21K |
| Reasoning | C | Runs with offload | 20.9 tok/s | 10935 ms | 21K |
| RAG | D | Very compromised (needs ~1.1 GB host RAM) | 13.1 tok/s | 26830 ms | 21K |
Quantization options
How Codestral 22B v0.1 (22B params) fits at each quantization level on RTX 4000 Ada 20GB (20.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 8.6 GB | Low | C50 |
Q3_K_S | 3 | 10.8 GB | Low | C51 |
NVFP4 | 4 | 12.3 GB | Medium | C50 |
Q4_K_MBest for your GPU | 4 | 13.4 GB | Medium | C50 |
Q5_K_M | 5 | 15.8 GB | High | F0 |
Q6_K | 6 | 18.0 GB | High | F0 |
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-bartowski--codestral-22b-v0-1-gguf && lms server start升级选项
能流畅运行 Codestral 22B v0.1 的硬件
RTX 3090 24GB经济之选RTX 4090 24GB最佳性价比24 GB VRAM (+4)1008 GB/s (+648)
B
Raises estimated decode speed by about 173%.57.1 tok/s 解码
Raises estimated decode speed by about 173%.
~$1,599 MSRP
RTX PRO 4000 Blackwell 24GBNVIDIA 升级24 GB VRAM (+4)672 GB/s (+312)
C
Raises estimated decode speed by about 101%.42.1 tok/s 解码
Raises estimated decode speed by about 101%.
~$1,599 MSRP
Frequently asked questions
Can RTX 4000 Ada 20GB run Codestral 22B v0.1?
Yes, RTX 4000 Ada 20GB can run Codestral 22B v0.1 with a C grade (Runs with offload). Expected decode speed: 20.9 tok/s.
How much VRAM does Codestral 22B v0.1 need?
Codestral 22B v0.1 (22B parameters) requires approximately 19.2 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 RTX 4000 Ada 20GB?
On RTX 4000 Ada 20GB, Codestral 22B v0.1 achieves approximately 20.9 tokens per second decode speed with a time-to-first-token of 9253ms using Q4_K_M quantization.
Can RTX 4000 Ada 20GB run Codestral 22B v0.1 for coding?
For coding workloads, Codestral 22B v0.1 on RTX 4000 Ada 20GB receives a C grade with 20.9 tok/s and 21K context.
What context window can Codestral 22B v0.1 use on RTX 4000 Ada 20GB?
On RTX 4000 Ada 20GB, Codestral 22B v0.1 can safely use up to 21K tokens of context. The model's official context limit is —, but available memory constrains the safe maximum.
What should I upgrade first if Codestral 22B v0.1 feels slow on RTX 4000 Ada 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-bartowski--codestral-22b-v0-1-gguf-on-rtx-4000-ada-20gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview: