Codestral 2 25.08 needs ~23.3 GB VRAM. NVIDIA L40 48GB has 48.0 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
54.0 tok/s
TTFT
3586 ms
Safe context
178K
Memory
23.3 GB / 48.0 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 | A | Runs well | 54.0 tok/s | 1956 ms | 178K |
| Coding | A | Runs well | 54.0 tok/s | 3586 ms | 178K |
| Agentic Coding | S | Runs well | 54.0 tok/s | 5216 ms | 178K |
| Reasoning | A | Runs well | 54.0 tok/s | 4238 ms | 178K |
| RAG | S | Runs well | 54.0 tok/s | 6520 ms | 178K |
How Codestral 2 25.08 (22B params) fits at each quantization level on NVIDIA L40 48GB (48.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 8.6 GB | Low | A77 |
Q3_K_S | 3 | 10.8 GB | Low | A77 |
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 | 101.9 tok/s | ||
| 27B | S | 44.2 tok/s |
Yes, NVIDIA L40 48GB can run Codestral 2 25.08 with a A grade (Runs well). Expected decode speed: 54.0 tok/s.
Codestral 2 25.08 (22B parameters) requires approximately 23.3 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 NVIDIA L40 48GB, Codestral 2 25.08 achieves approximately 54.0 tokens per second decode speed with a time-to-first-token of 3586ms using Q4_K_M quantization.
For coding workloads, Codestral 2 25.08 on NVIDIA L40 48GB receives a A grade with 54.0 tok/s and 178K context.
On NVIDIA L40 48GB, Codestral 2 25.08 can safely use up to 178K 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-l40-48gb" 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 |
| A78 |
Q4_K_M | 4 | 13.4 GB | Medium | A78 |
Q5_K_M | 5 | 15.8 GB | High | A79 |
Q6_K | 6 | 18.0 GB | High | A80 |
Q8_0Best for your GPU | 8 | 23.5 GB | Very High | A82 |
F16 | 16 | 45.1 GB | Maximum | F0 |
| 27B | S | 44.3 tok/s |
| 35B | S | 85.6 tok/s |
| 30B | S | 105.4 tok/s |