Codestral 22B v0.1 needs ~18.5 GB VRAM. Tesla P100 16GB has 16.0 GB. With Q4_K_M quantization, expect ~17 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
2.5 GB over capacity — needs offload or smaller quantization
Fit status
Very compromised (needs ~1.8 GB host RAM)
Decode
17.1 tok/s
TTFT
11342 ms
Safe context
4K
Memory
18.5 GB / 16.0 GB
Offload
10%
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.
Older PCIe generation
PCIe 3.0 is workable, but it compounds the penalty when you offload heavily or try to scale across multiple cards.
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 1.8 GB of extra host RAM just for the offloaded portion, before OS and other tools.
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | D | Runs with offload (needs ~0.9 GB host RAM) | 20.0 tok/s | 5279 ms | 4K |
| Coding | D | Very compromised (needs ~1.8 GB host RAM) | 17.1 tok/s | 11342 ms | 4K |
| Agentic Coding | F | Too heavy | 12.8 tok/s | 21971 ms | 4K |
| Reasoning | D | Very compromised (needs ~1.8 GB host RAM) | 17.1 tok/s | 13404 ms | 4K |
| RAG | F | Too heavy | 12.8 tok/s | 27464 ms | 4K |
How Codestral 22B v0.1 (22B params) fits at each quantization level on Tesla P100 16GB (16.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 8.6 GB | Low | C51 |
Q3_K_SBest for your GPU | 3 | 10.8 GB | Low | C51 |
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 22B v0.1 on your machine.
Run
lms load hf-bartowski--codestral-22b-v0-1-gguf && lms server startUpgrade options
RTX 4000 Ada 20GBBudget pickRemoves host-memory offload, which is usually the single biggest latency and throughput win.
Adds memory headroom for longer context windows and future model growth.
~$1,250 MSRP
RTX 3090 24GBBest valueRemoves host-memory offload, which is usually the single biggest latency and throughput win.
Raises estimated decode speed by about 133%.
~$1,499 MSRP
RTX PRO 4000 Blackwell 24GBNVIDIA upgradeRemoves host-memory offload, which is usually the single biggest latency and throughput win.
Raises estimated decode speed by about 146%.
~$1,599 MSRP
Yes, Tesla P100 16GB can run Codestral 22B v0.1 with a D grade (Very compromised (needs ~1.8 GB host RAM)). Expected decode speed: 17.1 tok/s.
Codestral 22B v0.1 (22B parameters) requires approximately 18.5 GB of memory with Q4_K_M quantization.
The recommended quantization for Codestral 22B v0.1 is Q4_K_M, which balances quality and memory efficiency.
On Tesla P100 16GB, Codestral 22B v0.1 achieves approximately 17.1 tokens per second decode speed with a time-to-first-token of 11342ms using Q4_K_M quantization.
For coding workloads, Codestral 22B v0.1 on Tesla P100 16GB receives a D grade with 17.1 tok/s and 4K context.
On Tesla P100 16GB, Codestral 22B v0.1 can safely use up to 4K tokens of context. The model's official context limit is —, 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/hf-bartowski--codestral-22b-v0-1-gguf-on-tesla-p100-16gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview: