Magistral Small 2507 needs ~20.7 GB VRAM. Tesla P40 24GB has 24.0 GB. With Q4_K_M quantization, expect ~14 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
Tight fit
Decode
15.0 tok/s
TTFT
12915 ms
Safe context
38K
Memory
20.7 GB / 24.0 GB
This setup is broadly balanced for this model.
Older PCIe generation
PCIe 3.0 is workable, but it compounds the penalty when you offload heavily or try to scale across multiple cards.
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | S | Runs well | 15.0 tok/s | 7045 ms | 38K |
| Coding | S | Tight fit | 13.9 tok/s | 13884 ms | 38K |
| Agentic Coding | S | Runs with offload | 15.0 tok/s | 18786 ms | 38K |
| Reasoning | S | Tight fit | 15.0 tok/s | 15264 ms | 38K |
| RAG | S | Runs with offload | 15.0 tok/s | 23483 ms | 38K |
How Magistral Small 2507 (24B params) fits at each quantization level on Tesla P40 24GB (24.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 9.4 GB | Low | S90 |
Q3_K_S | 3 | 11.8 GB | Low | S92 |
NVFP4 | 4 |
Copy-paste commands to run Magistral Small 2507 on your machine.
Run
ollama run magistralYour hardware
| Model | Params | Grade | Decode | Capabilities |
|---|---|---|---|---|
| 30.5B | S | 30.9 tok/s | ||
| 27B | S | 13.4 tok/s |
Yes, Tesla P40 24GB can run Magistral Small 2507 with a S grade (Tight fit). Expected decode speed: 13.9 tok/s.
Magistral Small 2507 (24B parameters) requires approximately 20.7 GB of memory with Q4_K_M quantization.
The recommended quantization for Magistral Small 2507 is Q4_K_M, which balances quality and memory efficiency.
On Tesla P40 24GB, Magistral Small 2507 achieves approximately 13.9 tokens per second decode speed with a time-to-first-token of 13884ms using Q4_K_M quantization.
For coding workloads, Magistral Small 2507 on Tesla P40 24GB receives a S grade with 13.9 tok/s and 38K context.
On Tesla P40 24GB, Magistral Small 2507 can safely use up to 38K tokens of context. The model's official context limit is 131K, 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/magistral-small-2507-on-tesla-p40-24gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview:
13.4 GB |
| Medium |
| S92 |
Q4_K_M | 4 | 14.6 GB | Medium | S91 |
Q5_K_MBest for your GPU | 5 | 17.3 GB | High | S91 |
Q6_K | 6 | 19.7 GB | High | F0 |
Q8_0 | 8 | 25.7 GB | Very High | F0 |
F16 | 16 | 49.2 GB | Maximum | F0 |
| 27B | S | 13.4 tok/s |
| 30B | S | 31.9 tok/s |
| 35B | A | 16.7 tok/s |