MacBook Pro M3 Pro 36GB经济之选
36 GB Unified (+4)
C
This setup is broadly balanced for this model.8.5 tok/s 解码
~$1,999 MSRP
Can Codestral 21B Pruned i1 run on MacBook Pro M1 Max 32GB?
YES — Tight Fit
C48Usable
Estimated from fit model
Codestral 21B Pruned i1 needs ~19.6 GB VRAM. MacBook Pro M1 Max 32GB has 23.0 GB. With Q4_K_M quantization, expect ~17 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) — 19.6 GB, 17.2 tok/s, Tight fit
19.6 GB required23.0 GB available
85% VRAM used
Fit status
Tight fit
Decode
17.2 tok/s
TTFT
11273 ms
Safe context
38K
Memory
19.6 GB / 23.0 GB
Memory breakdown
Weights12.8 GB
KV Cache2.5 GB
Runtime0.9 GB
Headroom3.5 GB
See how fast it feels
See how fast it feelsCodestral 21B Pruned i1 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: 17.2 tok/s decode · 11.3s TTFT (warm) · 43 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 | C | Runs well | 17.2 tok/s | 6149 ms | 38K |
| Coding | C | Tight fit | 17.2 tok/s | 11273 ms | 38K |
| Agentic Coding | C | Runs with offload | 17.2 tok/s | 16397 ms | 38K |
| Reasoning | C | Tight fit | 17.2 tok/s | 13322 ms | 38K |
| RAG | C | Runs with offload | 17.2 tok/s | 20496 ms | 38K |
Quantization options
How Codestral 21B Pruned i1 (21B params) fits at each quantization level on MacBook Pro M1 Max 32GB (23.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 8.2 GB | Low | C48 |
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
MacBook Pro M4 Max 36GB最佳性价比
36 GB Unified (+4)410 GB/s (+10)
C
Raises estimated decode speed by about 63%.28 tok/s 解码
Raises estimated decode speed by about 63%.
~$2,499 MSRP
MacBook Pro M4 Max 48GBApple 升级
48 GB Unified (+16)546 GB/s (+146)
C
Raises estimated decode speed by about 105%.35.2 tok/s 解码
Raises estimated decode speed by about 105%.
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 21B Pruned i1?
Yes, MacBook Pro M1 Max 32GB can run Codestral 21B Pruned i1 with a C grade (Tight fit). Expected decode speed: 17.2 tok/s.
How much VRAM does Codestral 21B Pruned i1 need?
Codestral 21B Pruned i1 (21B parameters) requires approximately 19.6 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 MacBook Pro M1 Max 32GB?
On MacBook Pro M1 Max 32GB, Codestral 21B Pruned i1 achieves approximately 17.2 tokens per second decode speed with a time-to-first-token of 11273ms using Q4_K_M quantization.
Can MacBook Pro M1 Max 32GB run Codestral 21B Pruned i1 for coding?
For coding workloads, Codestral 21B Pruned i1 on MacBook Pro M1 Max 32GB receives a C grade with 17.2 tok/s and 38K context.
What context window can Codestral 21B Pruned i1 use on MacBook Pro M1 Max 32GB?
On MacBook Pro M1 Max 32GB, Codestral 21B Pruned i1 can safely use up to 38K tokens of context. The model's official context limit is —, but available memory constrains the safe maximum.
Is unified memory on MacBook Pro M1 Max 32GB as fast as VRAM for Codestral 21B Pruned i1?
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/hf-mradermacher--codestral-21b-pruned-i1-gguf-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: