RTX PRO 5000 Blackwell 48GB经济之选1344 GB/s (+944)
B
Raises estimated decode speed by about 347%.85.9 tok/s 解码
Raises estimated decode speed by about 347%.
Adds memory headroom for longer context windows and future model growth.
~$4,999 MSRP
Can Codestral 22B run on MacBook Pro M3 Max 48GB?
YES — Runs Great
B60Good
Estimated from fit model
Codestral 22B needs ~21.9 GB VRAM. MacBook Pro M3 Max 48GB has 34.6 GB. With Q4_K_M quantization, expect ~18 tok/s.
Runtime: llama.cppCapacity: RoomyBandwidth: LowStack: 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.
Select quantization to explore
Q4_K_M (Medium quality) — 21.9 GB, 19.2 tok/s, Runs well
21.9 GB required34.6 GB available
63% VRAM used
Fit status
Runs well
Decode
19.2 tok/s
TTFT
10070 ms
Safe context
33K
Memory
21.9 GB / 34.6 GB
Memory breakdown
Weights13.4 GB
KV Cache2.4 GB
Runtime0.9 GB
Headroom5.2 GB
See how fast it feels
See how fast it feelsCodestral 22B on MacBook Pro M3 Max 48GB
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: 19.2 tok/s decode · 10.1s TTFT (warm) · 48 tok/s prefill
What limits this setup
This setup is broadly balanced for this model.
Shared-memory contention still exists
The OS, browser, and inference runtime all compete for the same physical memory pool, so real-world headroom is less forgiving than raw capacity suggests.
Best improvement path
Performance by workload
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | B | Runs well | 19.2 tok/s | 5493 ms | 33K |
| Coding | B | Runs well | 17.9 tok/s | 10825 ms | 33K |
| Agentic Coding | B | Runs well | 19.2 tok/s | 14648 ms | 33K |
| Reasoning | B | Runs well | 19.2 tok/s | 11901 ms | 33K |
| RAG | B | Runs well | 19.2 tok/s | 18309 ms | 33K |
Quantization options
How Codestral 22B (22B params) fits at each quantization level on MacBook Pro M3 Max 48GB (34.6 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 8.6 GB | Low | C55 |
Q3_K_S | 3 | 10.8 GB | Low | B56 |
NVFP4 | 4 | 12.3 GB | Medium | B56 |
Q4_K_M | 4 | 13.4 GB | Medium | B57 |
Q5_K_M | 5 | 15.8 GB | High | B58 |
Q6_K | 6 | 18.0 GB | High | B59 |
Q8_0Best for your GPU | 8 | 23.5 GB | Very High | B59 |
F16 | 16 | 45.1 GB | Maximum | F0 |
Get started
Copy-paste commands to run Codestral 22B on your machine.
Run
ollama run codestral升级选项
能流畅运行 Codestral 22B 的硬件
Frequently asked questions
Can MacBook Pro M3 Max 48GB run Codestral 22B?
Yes, MacBook Pro M3 Max 48GB can run Codestral 22B with a B grade (Runs well). Expected decode speed: 17.9 tok/s.
How much VRAM does Codestral 22B need?
Codestral 22B (22B parameters) requires approximately 21.9 GB of memory with Q4_K_M quantization.
What is the best quantization for Codestral 22B?
The recommended quantization for Codestral 22B is Q4_K_M, which balances quality and memory efficiency.
What speed will Codestral 22B run at on MacBook Pro M3 Max 48GB?
On MacBook Pro M3 Max 48GB, Codestral 22B achieves approximately 17.9 tokens per second decode speed with a time-to-first-token of 10825ms using Q4_K_M quantization.
Can MacBook Pro M3 Max 48GB run Codestral 22B for coding?
For coding workloads, Codestral 22B on MacBook Pro M3 Max 48GB receives a B grade with 17.9 tok/s and 33K context.
What context window can Codestral 22B use on MacBook Pro M3 Max 48GB?
On MacBook Pro M3 Max 48GB, Codestral 22B can safely use up to 33K tokens of context. The model's official context limit is 33K, but available memory constrains the safe maximum.
Is unified memory on MacBook Pro M3 Max 48GB as fast as VRAM for Codestral 22B?
Not always. MacBook Pro M3 Max 48GB can often fit larger models thanks to unified memory, but a discrete GPU with dedicated high-bandwidth VRAM may still decode faster once the model fits. For this combination, the important distinction is capacity versus sustained throughput.
Embed this result▼
Paste this snippet into any page to show a live fit card.
<iframe src="https://willitrunai.com/embed/codestral-22b-on-m3-max-48gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview: