Codestral 2 25.08 needs ~26.4 GB VRAM. NVIDIA H20 96GB has 96.0 GB. With Q4_K_M quantization, expect ~216 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
231.8 tok/s
TTFT
835 ms
Safe context
256K
Memory
26.4 GB / 96.0 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 | 231.8 tok/s | 456 ms | 256K |
| Coding | A | Runs well | 215.6 tok/s | 898 ms | 256K |
| Agentic Coding | A | Runs well | 231.8 tok/s | 1215 ms | 256K |
| Reasoning | A | Runs well | 231.8 tok/s | 987 ms | 256K |
| RAG | A | Runs well | 231.8 tok/s | 1519 ms | 256K |
How Codestral 2 25.08 (22B params) fits at each quantization level on NVIDIA H20 96GB (96.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 8.6 GB | Low | A74 |
Q3_K_S | 3 | 10.8 GB | Low | A74 |
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 |
|---|---|---|---|---|
| 123B | S | 47 tok/s | ||
| 30.5B | S |
Yes, NVIDIA H20 96GB can run Codestral 2 25.08 with a A grade (Runs well). Expected decode speed: 215.6 tok/s.
Codestral 2 25.08 (22B parameters) requires approximately 26.4 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 H20 96GB, Codestral 2 25.08 achieves approximately 215.6 tokens per second decode speed with a time-to-first-token of 898ms using Q4_K_M quantization.
For coding workloads, Codestral 2 25.08 on NVIDIA H20 96GB receives a A grade with 215.6 tok/s and 256K context.
On NVIDIA H20 96GB, Codestral 2 25.08 can safely use up to 256K 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-h20-96gb" 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 |
| A74 |
Q4_K_M | 4 | 13.4 GB | Medium | A74 |
Q5_K_M | 5 | 15.8 GB | High | A74 |
Q6_K | 6 | 18.0 GB | High | A75 |
Q8_0 | 8 | 23.5 GB | Very High | A75 |
F16Best for your GPU | 16 | 45.1 GB | Maximum | A80 |
| 489.9 tok/s |
| 27B | S | 212.5 tok/s |
| 27B | S | 132.4 tok/s |
| 122B | S | 130.3 tok/s |