Phi 4 reasoning vision 15B needs ~22.2 GB VRAM. MacBook Pro M2 Max 96GB has 69.1 GB. With Q4_K_M quantization, expect ~25 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
25.4 tok/s
TTFT
7636 ms
Safe context
443K
Memory
22.2 GB / 69.1 GB
This setup is broadly balanced for this model.
Shared-memory contention still exists
The OS, browser, and inference runtime all compete for the same physical memory pool, so real-world headroom is less forgiving than raw capacity suggests.
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | C | Runs well | 25.4 tok/s | 4165 ms | 443K |
| Coding | C | Runs well | 25.4 tok/s | 7636 ms | 443K |
| Agentic Coding | C | Runs well | 25.4 tok/s | 11106 ms | 443K |
| Reasoning | C | Runs well | 25.4 tok/s | 9024 ms | 443K |
| RAG | C | Runs well | 25.4 tok/s | 13883 ms | 443K |
How Phi 4 reasoning vision 15B (15B params) fits at each quantization level on MacBook Pro M2 Max 96GB (69.1 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 5.9 GB | Low | C40 |
Q3_K_S | 3 | 7.4 GB | Low | C40 |
NVFP4 | 4 | 8.4 GB | Medium | C41 |
Q4_K_M | 4 | 9.2 GB | Medium | C41 |
Q5_K_M | 5 | 10.8 GB | High | C41 |
Q6_K | 6 | 12.3 GB | High | C41 |
Q8_0 | 8 | 16.1 GB | Very High | C42 |
F16Best for your GPU | 16 | 30.7 GB | Maximum | C45 |
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 startOpciones de mejora
Sube la velocidad estimada de decodificación alrededor de un 100%.
Añade margen de memoria para más contexto y para que el modelo envejezca mejor.
~$3,999 MSRP
Sube la velocidad estimada de decodificación alrededor de un 89%.
Añade margen de memoria para más contexto y para que el modelo envejezca mejor.
~$3,999 MSRP
Sube la velocidad estimada de decodificación alrededor de un 37%.
Añade margen de memoria para más contexto y para que el modelo envejezca mejor.
~$4,999 MSRP
Yes, MacBook Pro M2 Max 96GB can run Phi 4 reasoning vision 15B with a C grade (Runs well). Expected decode speed: 25.4 tok/s.
Phi 4 reasoning vision 15B (15B parameters) requires approximately 22.2 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 MacBook Pro M2 Max 96GB, Phi 4 reasoning vision 15B achieves approximately 25.4 tokens per second decode speed with a time-to-first-token of 7636ms using Q4_K_M quantization.
For coding workloads, Phi 4 reasoning vision 15B on MacBook Pro M2 Max 96GB receives a C grade with 25.4 tok/s and 443K context.
On MacBook Pro M2 Max 96GB, Phi 4 reasoning vision 15B can safely use up to 443K tokens of context. The model's official context limit is —, but available memory constrains the safe maximum.
Not always. MacBook Pro M2 Max 96GB can often fit larger models thanks to unified memory, but a discrete GPU with dedicated high-bandwidth VRAM may still decode faster once the model fits. For this combination, the important distinction is capacity versus sustained throughput.
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-m2-max-96gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview: