Codestral 22B needs ~18.2 GB but GTX 1080 Ti 11GB only has 11.0 GB. Try a smaller quantization or lighter model.
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
7.2 GB over capacity — needs offload or smaller quantization
Fit status
Too heavy
Decode
5.5 tok/s
TTFT
34896 ms
Safe context
4K
Memory
18.2 GB / 11.0 GB
Offload
40%
Usable VRAM is the main blocker for this model.
Not enough usable memory
The model needs 18.2 GB, but this setup only exposes 11.0 GB of usable VRAM.
Older PCIe generation
PCIe 3.0 is workable, but it compounds the penalty when you offload heavily or try to scale across multiple cards.
Add more VRAM headroom
The first useful upgrade is more dedicated VRAM so you can fit the model without shrinking context or dropping to a much lower quant.
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | F | Too heavy | 6.5 tok/s | 16337 ms | 4K |
| Coding | F | Too heavy | 5.2 tok/s | 37513 ms | 4K |
| Agentic Coding | F | Too heavy | 4.2 tok/s | 66956 ms | 4K |
| Reasoning | F | Too heavy | 5.5 tok/s | 41240 ms | 4K |
| RAG | F | Too heavy | 4.2 tok/s | 83695 ms | 4K |
How Codestral 22B (22B params) fits at each quantization level on GTX 1080 Ti 11GB (11.0 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 |
アップグレードオプション
RTX 5060 Ti 16GBコスパ最良Makes the model fit on the accelerator instead of staying completely out of reach.
Raises estimated decode speed by about 125%.
〜$449 MSRP
RTX 4060 Ti 16GBNVIDIAアップグレードMakes the model fit on the accelerator instead of staying completely out of reach.
Raises estimated decode speed by about 65%.
〜$499 MSRP
RTX 4000 Ada 20GBコスパ重視Makes 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 4090 24GB最大の飛躍Makes 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.
〜$1,599 MSRP
No, Codestral 22B requires more memory than GTX 1080 Ti 11GB provides.
Codestral 22B (22B parameters) requires approximately 18.2 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 GTX 1080 Ti 11GB, Codestral 22B achieves approximately 5.2 tokens per second decode speed with a time-to-first-token of 37513ms using Q4_K_M quantization.
For coding workloads, Codestral 22B on GTX 1080 Ti 11GB receives a F grade with 5.2 tok/s and 4K context.
On GTX 1080 Ti 11GB, Codestral 22B can safely use up to 4K tokens of context. The model's official context limit is 33K, but available memory constrains the safe maximum.
Add more VRAM headroom. The first useful upgrade is more dedicated VRAM so you can fit the model without shrinking context or dropping to a much lower quant.
Paste this snippet into any page to show a live fit card.
<iframe src="https://willitrunai.com/embed/codestral-22b-on-gtx-1080-ti-11gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview:
