Codestral 2 25.08 needs ~13.1 GB VRAM. RTX A2000 12GB has 12.0 GB. With Q2_K quantization, expect ~13 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
6.0 GB over capacity — needs offload or smaller quantization
Fit status
Too heavy
Decode
5.2 tok/s
TTFT
37546 ms
Safe context
4K
Memory
18.0 GB / 12.0 GB
Offload
30%
It fits through host-memory offload, and offload is the main reason performance drops.
CPU or host-memory offload is active
About 10% of the working set spills out of accelerator memory, which usually hurts latency and sustained decode throughput.
Very little memory headroom
You can run the model, but there is not much room left for longer context, bigger batches, extra apps, or future model updates.
Remove offload with more accelerator memory
Prioritize a GPU or unified-memory tier that fits the whole model natively. Removing offload usually helps more than small compute gains.
Buy headroom, not only minimum fit
A slightly larger memory tier gives you safer context growth and makes the recommendation more future-proof.
Increase host RAM if you keep offloading
This setup may need roughly 0.7 GB of extra host RAM just for the offloaded portion, before OS and other tools.
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | F | Too heavy | 6.0 tok/s | 17659 ms | 4K |
| Coding | F | Too heavy | 5.2 tok/s | 37546 ms | 4K |
| Agentic Coding | F | Too heavy | 3.9 tok/s | 71416 ms | 4K |
| Reasoning | F | Too heavy | 5.2 tok/s | 44372 ms | 4K |
| RAG | F | Too heavy | 3.9 tok/s | 89270 ms | 4K |
How Codestral 2 25.08 (22B params) fits at each quantization level on RTX A2000 12GB (12.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 8.6 GB | Low | F0 |
Q3_K_S | 3 | 10.8 GB | Low | F0 |
NVFP4 | 4 | 12.3 GB | Medium | F0 |
Q4_K_M | 4 | 13.4 GB | Medium | F0 |
Q5_K_M | 5 | 15.8 GB | High | F0 |
Q6_K | 6 | 18.0 GB | High | F0 |
Q8_0 | 8 | 23.5 GB | Very High | F0 |
F16 | 16 | 45.1 GB | Maximum | F0 |
Copy-paste commands to run Codestral 2 25.08 on your machine.
Run
lms load codestral-2508 && lms server startUpgrade options
RTX 5060 Ti 16GBBest valueMakes the model fit on the accelerator instead of staying completely out of reach.
Raises estimated decode speed by about 75%.
~$449 MSRP
RTX 4060 Ti 16GBNVIDIA upgradeMakes the model fit on the accelerator instead of staying completely out of reach.
Adds memory headroom for longer context windows and future model growth.
~$499 MSRP
RTX 4000 Ada 20GBBudget pickMakes the model fit on the accelerator instead of staying completely out of reach.
Removes host-memory offload, which is usually the single biggest latency and throughput win.
~$1,250 MSRP
RTX 5090 Laptop 24GBBiggest leapMakes the model fit on the accelerator instead of staying completely out of reach.
Removes host-memory offload, which is usually the single biggest latency and throughput win.
Yes, RTX A2000 12GB can run Codestral 2 25.08 at Q2_K quantization (Very compromised (needs ~0.7 GB host RAM)). The recommended Q4_K_M requires 18.0 GB which exceeds available memory, but at Q2_K it needs only 13.1 GB. Expected decode speed: 13.3 tok/s.
Codestral 2 25.08 (22B parameters) requires approximately 18.0 GB at Q4_K_M quantization. On RTX A2000 12GB, it fits at Q2_K using 13.1 GB.
The recommended quantization is Q4_K_M, but on RTX A2000 12GB the best fitting quantization is Q2_K, which uses 13.1 GB.
On RTX A2000 12GB, Codestral 2 25.08 achieves approximately 13.3 tokens per second decode speed with a time-to-first-token of 14583ms using Q2_K quantization.
For coding workloads, Codestral 2 25.08 on RTX A2000 12GB receives a F grade with 5.2 tok/s and 4K context.
On RTX A2000 12GB, Codestral 2 25.08 can safely use up to 9K tokens of context at Q2_K quantization. The model's official context limit is 256K, but available memory constrains the safe maximum.
Remove offload with more accelerator memory. Prioritize a GPU or unified-memory tier that fits the whole model natively. Removing offload usually helps more than small compute gains.
Paste this snippet into any page to show a live fit card.
<iframe src="https://willitrunai.com/embed/codestral-2-25.08-on-a2000-12gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview: