Codestral 2 25.08 needs ~20.0 GB VRAM. RTX PRO 4500 Blackwell 32GB has 32.0 GB. With Q4_K_M quantization, expect ~54 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
53.8 tok/s
TTFT
3596 ms
Safe context
95K
Memory
20.0 GB / 32.0 GB
This setup is broadly balanced for this model.
No major red flags
This recommendation has enough memory headroom and acceptable estimated speed for the selected workload.
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | S | Runs well | 53.8 tok/s | 1961 ms | 95K |
| Coding | S | Runs well | 53.8 tok/s | 3596 ms | 95K |
| Agentic Coding | S | Runs well | 53.8 tok/s | 5230 ms | 95K |
| Reasoning | S | Runs well | 53.8 tok/s | 4250 ms | 95K |
| RAG | S | Runs well | 53.8 tok/s | 6538 ms | 95K |
How Codestral 2 25.08 (22B params) fits at each quantization level on RTX PRO 4500 Blackwell 32GB (32.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 8.6 GB | Low | A80 |
Q3_K_S | 3 | 10.8 GB | Low | A81 |
NVFP4 | 4 |
Copy-paste commands to run Codestral 2 25.08 on your machine.
Run
lms load codestral-2508 && lms server startYour hardware
| Model | Params | Grade | Decode | Capabilities |
|---|---|---|---|---|
| 30.5B | S | 113.8 tok/s | ||
| 27B | S | 49.4 tok/s |
Yes, RTX PRO 4500 Blackwell 32GB can run Codestral 2 25.08 with a S grade (Runs well). Expected decode speed: 53.8 tok/s.
Codestral 2 25.08 (22B parameters) requires approximately 20.0 GB of memory with Q4_K_M quantization.
The recommended quantization for Codestral 2 25.08 is Q4_K_M, which balances quality and memory efficiency.
On RTX PRO 4500 Blackwell 32GB, Codestral 2 25.08 achieves approximately 53.8 tokens per second decode speed with a time-to-first-token of 3596ms using Q4_K_M quantization.
For coding workloads, Codestral 2 25.08 on RTX PRO 4500 Blackwell 32GB receives a S grade with 53.8 tok/s and 95K context.
On RTX PRO 4500 Blackwell 32GB, Codestral 2 25.08 can safely use up to 95K tokens of context. The model's official context limit is 256K, but available memory constrains the safe maximum.
Paste this snippet into any page to show a live fit card.
<iframe src="https://willitrunai.com/embed/codestral-2-25.08-on-rtx-pro-4500-blackwell-32gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview:
12.3 GB |
| Medium |
| A81 |
Q4_K_M | 4 | 13.4 GB | Medium | A82 |
Q5_K_M | 5 | 15.8 GB | High | A83 |
Q6_K | 6 | 18.0 GB | High | A84 |
Q8_0Best for your GPU | 8 | 23.5 GB | Very High | A83 |
F16 | 16 | 45.1 GB | Maximum | F0 |
| 27B | S | 34.3 tok/s |
| 35B | S | 95.6 tok/s |
| 30B | S | 117.7 tok/s |