Phi 4 reasoning vision 15B needs ~14.5 GB VRAM. Tesla P40 24GB has 24.0 GB. With Q4_K_M quantization, expect ~22 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
22.3 tok/s
TTFT
8678 ms
Safe context
102K
Memory
14.5 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 | C | Runs well | 22.3 tok/s | 4733 ms | 102K |
| Coding | C | Runs well | 22.3 tok/s | 8678 ms | 102K |
| Agentic Coding | C | Runs well | 22.3 tok/s | 12622 ms | 102K |
| Reasoning | C | Runs well | 22.3 tok/s | 10255 ms | 102K |
| RAG | C | Runs well | 22.3 tok/s | 15777 ms | 102K |
How Phi 4 reasoning vision 15B (15B params) fits at each quantization level on Tesla P40 24GB (24.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 5.9 GB | Low | C46 |
Q3_K_S | 3 | 7.4 GB | Low | C47 |
NVFP4 | 4 | 8.4 GB | Medium | C47 |
Q4_K_M | 4 | 9.2 GB | Medium | C48 |
Q5_K_M | 5 | 10.8 GB | High | C49 |
Q6_K | 6 | 12.3 GB | High | C50 |
Q8_0Best for your GPU | 8 | 16.1 GB | Very High | C50 |
F16 | 16 | 30.7 GB | Maximum | F0 |
Copy-paste commands to run Phi 4 reasoning vision 15B on your machine.
Run
lms load hf-jamesburton--phi-4-reasoning-vision-15b-gguf && lms server startUpgrade options
RTX 5090 32GBBudget pickRaises estimated decode speed by about 488%.
Adds memory headroom for longer context windows and future model growth.
~$1,999 MSRP
RTX PRO 4500 Blackwell 32GBBest valueRaises estimated decode speed by about 269%.
Adds memory headroom for longer context windows and future model growth.
~$2,499 MSRP
NVIDIA V100 32GBNVIDIA upgradeRaises estimated decode speed by about 196%.
Adds memory headroom for longer context windows and future model growth.
~$8,999 MSRP
Yes, Tesla P40 24GB can run Phi 4 reasoning vision 15B with a C grade (Runs well). Expected decode speed: 22.3 tok/s.
Phi 4 reasoning vision 15B (15B parameters) requires approximately 14.5 GB of memory with Q4_K_M quantization.
The recommended quantization for Phi 4 reasoning vision 15B is Q4_K_M, which balances quality and memory efficiency.
On Tesla P40 24GB, Phi 4 reasoning vision 15B achieves approximately 22.3 tokens per second decode speed with a time-to-first-token of 8678ms using Q4_K_M quantization.
For coding workloads, Phi 4 reasoning vision 15B on Tesla P40 24GB receives a C grade with 22.3 tok/s and 102K context.
On Tesla P40 24GB, Phi 4 reasoning vision 15B can safely use up to 102K tokens of context. The model's official context limit is —, 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/hf-jamesburton--phi-4-reasoning-vision-15b-gguf-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: