RTX 5090 32GBBudget pick1792 GB/s (+1382)
B
Raises estimated decode speed by about 143%.72.4 tok/s decode
Raises estimated decode speed by about 143%.
Adds memory headroom for longer context windows and future model growth.
~$1,999 MSRP
Codestral 22B needs ~20.6 GB VRAM. MacBook Pro M4 Max 36GB has 25.9 GB. With Q4_K_M quantization, expect ~30 tok/s.
Operating mode
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
Fit status
Runs well
Decode
29.8 tok/s
TTFT
6489 ms
Safe context
33K
Memory
20.6 GB / 25.9 GB
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.
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | B | Runs well | 29.8 tok/s | 3539 ms | 33K |
| Coding | B | Runs well | 29.8 tok/s | 6489 ms | 33K |
| Agentic Coding | B | Tight fit | 29.8 tok/s | 9438 ms | 33K |
| Reasoning | B | Runs well | 29.8 tok/s | 7668 ms | 33K |
| RAG | B | Tight fit | 29.8 tok/s | 11798 ms | 33K |
How Codestral 22B (22B params) fits at each quantization level on MacBook Pro M4 Max 36GB (25.9 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 8.6 GB | Low | B57 |
Q3_K_S | 3 | 10.8 GB | Low | B59 |
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 | B59 |
Q8_0 | 8 | 23.5 GB | Very High | F0 |
F16 | 16 | 45.1 GB | Maximum | F0 |
Copy-paste commands to run Codestral 22B on your machine.
Run
ollama run codestralUpgrade options
RTX 5090 32GBBudget pickRaises estimated decode speed by about 143%.
Adds memory headroom for longer context windows and future model growth.
~$1,999 MSRP
RTX PRO 4500 Blackwell 32GBBest valueRaises estimated decode speed by about 92%.
Adds memory headroom for longer context windows and future model growth.
~$2,499 MSRP
Yes, MacBook Pro M4 Max 36GB can run Codestral 22B with a B grade (Runs well). Expected decode speed: 29.8 tok/s.
Codestral 22B (22B parameters) requires approximately 20.6 GB of memory with Q4_K_M quantization.
The recommended quantization for Codestral 22B is Q4_K_M, which balances quality and memory efficiency.
On MacBook Pro M4 Max 36GB, Codestral 22B achieves approximately 29.8 tokens per second decode speed with a time-to-first-token of 6489ms using Q4_K_M quantization.
For coding workloads, Codestral 22B on MacBook Pro M4 Max 36GB receives a B grade with 29.8 tok/s and 33K context.
On MacBook Pro M4 Max 36GB, 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.
Not always. MacBook Pro M4 Max 36GB 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.
Paste this snippet into any page to show a live fit card.
<iframe src="https://willitrunai.com/embed/codestral-22b-on-m4-max-36gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview: