MacBook Pro M3 Pro 36GB经济之选
36 GB Unified (+4)
B
This setup is broadly balanced for this model.8.8 tok/s 解码
~$1,999 MSRP
Can Codestral 22B run on MacBook Pro M1 Max 32GB?
YES — Tight Fit
B59Good
Estimated from fit model
Codestral 22B needs ~20.2 GB VRAM. MacBook Pro M1 Max 32GB has 23.0 GB. With Q4_K_M quantization, expect ~18 tok/s.
Runtime: llama.cppCapacity: TightBandwidth: 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) — 20.2 GB, 17.6 tok/s, Tight fit
20.2 GB required23.0 GB available
88% VRAM used
Fit status
Tight fit
Decode
17.6 tok/s
TTFT
10986 ms
Safe context
33K
Memory
20.2 GB / 23.0 GB
Memory breakdown
Weights13.4 GB
KV Cache2.4 GB
Runtime0.9 GB
Headroom3.5 GB
See how fast it feels
See how fast it feelsCodestral 22B on MacBook Pro M1 Max 32GB
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: 17.6 tok/s decode · 11.0s TTFT (warm) · 44 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 | Tight fit | 17.6 tok/s | 5992 ms | 33K |
| Coding | B | Tight fit | 17.6 tok/s | 10986 ms | 33K |
| Agentic Coding | B | Runs with offload | 17.6 tok/s | 15979 ms | 33K |
| Reasoning | B | Tight fit | 17.6 tok/s | 12983 ms | 33K |
| RAG | B | Runs with offload | 17.6 tok/s | 19974 ms | 33K |
Inference speed
Codestral 22B inference speed — tokens per second by GPU & Mac
Estimated decode speed (tokens/sec) for Codestral 22B at Q4_K_M across popular GPUs and Apple Silicon, using the fastest local runtime per device. Fastest is RTX 5090 32GB at ~96 tok/s. Speed is memory-bandwidth bound, so cards that fit the whole model in VRAM run far faster than ones that offload to system RAM.
| GPU / Mac | Memory | Quant | Speed (tok/s) | Fits? |
|---|---|---|---|---|
 RTX 5090 32GB | 32 GB | Q4_K_M | 96.2 | Fits |
| RTX 4090 24GB | 24 GB | Q4_K_M | 61.4 | Fits |
RX 7900 XTX 24GB | 24 GB | Q4_K_M | 55.4 | Fits |
| RTX 3090 24GB | 24 GB | Q4_K_M | 52.5 | Fits |
Mac Studio M3 Ultra 256GB | 256 GB | Q4_K_M | 44.6 | Fits |
MacBook Pro M4 Max 128GB | 128 GB | Q4_K_M | 37.4 | Fits |
MacBook Pro M4 Max 64GB | 64 GB | Q4_K_M | 37.4 | Fits |
Mac Studio M2 Ultra 128GB | 128 GB | Q4_K_M | 37.2 | Fits |
Mac Studio M1 Ultra 128GB | 128 GB | Q4_K_M | 35.2 | Fits |
| RTX 4080 Super 16GB | 16 GB | Q4_K_M | 26.5 | Heavy offload |
MacBook Pro M4 Pro 48GB | 48 GB | Q4_K_M | 23.6 | Fits |
MacBook Pro M3 Max 64GB | 64 GB | Q4_K_M | 19.2 | Fits |
MacBook Pro M1 Max 64GB | 64 GB | Q4_K_M | 17.6 | Fits |
| RTX 4070 12GB | 12 GB | Q4_K_M | 9.4 | Too big |
| RTX 3060 12GB | 12 GB | Q4_K_M | 5.9 | Too big |
| RTX 4060 8GB | 8 GB | Q4_K_M | 2.4 | Too big |
Estimates for single-stream decoding at Q4_K_M; real tokens/sec varies with prompt length, context, batch size, and runtime build. Prompt processing (prefill) is faster than the decode figures shown here.
Quantization options
How Codestral 22B (22B params) fits at each quantization level on MacBook Pro M1 Max 32GB (23.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 8.6 GB | Low | B58 |
Q3_K_S | 3 | 10.8 GB | Low | B60 |
NVFP4 | 4 | 12.3 GB | Medium | B60 |
Q4_K_M | 4 | 13.4 GB | Medium | B60 |
Q5_K_M | 5 | 15.8 GB | High | B60 |
Q6_KBest for your GPU | 6 | 18.0 GB | High | B60 |
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 on your machine.
Run
ollama run codestral升级选项
能流畅运行 Codestral 22B 的硬件
MacBook Pro M4 Max 36GB最佳性价比
36 GB Unified (+4)410 GB/s (+10)
B
Raises estimated decode speed by about 69%.29.8 tok/s 解码
Raises estimated decode speed by about 69%.
~$2,499 MSRP
MacBook Pro M4 Max 48GBApple 升级
48 GB Unified (+16)546 GB/s (+146)
B
Raises estimated decode speed by about 112%.37.4 tok/s 解码
Raises estimated decode speed by about 112%.
Adds memory headroom for longer context windows and future model growth.
~$2,499 MSRP
Frequently asked questions
Can MacBook Pro M1 Max 32GB run Codestral 22B?
Yes, MacBook Pro M1 Max 32GB can run Codestral 22B with a B grade (Tight fit). Expected decode speed: 17.6 tok/s.
How much VRAM does Codestral 22B need?
Codestral 22B (22B parameters) requires approximately 20.2 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 M1 Max 32GB?
On MacBook Pro M1 Max 32GB, Codestral 22B achieves approximately 17.6 tokens per second decode speed with a time-to-first-token of 10986ms using Q4_K_M quantization.
Can MacBook Pro M1 Max 32GB run Codestral 22B for coding?
For coding workloads, Codestral 22B on MacBook Pro M1 Max 32GB receives a B grade with 17.6 tok/s and 33K context.
What context window can Codestral 22B use on MacBook Pro M1 Max 32GB?
On MacBook Pro M1 Max 32GB, 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 M1 Max 32GB as fast as VRAM for Codestral 22B?
Not always. MacBook Pro M1 Max 32GB 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-m1-max-32gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview: