Phi 4 reasoning vision 15B needs ~14.4 GB VRAM. MacBook Air M3 24GB has 17.3 GB. With Q4_K_M quantization, expect ~7 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
7.4 tok/s
TTFT
26051 ms
Safe context
42K
Memory
14.4 GB / 17.3 GB
The model fits in shared memory, but shared-memory bandwidth is now the real limiter.
Fit does not mean dedicated-VRAM speed
Unified or shared memory can make a model technically fit, but sustained tokens per second may still trail a discrete high-bandwidth GPU with less total memory.
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.
Prioritize bandwidth, not only capacity
If this workload feels slow, the next useful step is often a GPU tier with materially faster memory bandwidth rather than only a small bump in capacity.
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | C | Runs well | 7.4 tok/s | 14209 ms | 42K |
| Coding | C | Tight fit | 7.4 tok/s | 26051 ms | 42K |
| Agentic Coding | C | Tight fit | 7.4 tok/s | 37892 ms | 42K |
| Reasoning | C | Tight fit | 7.4 tok/s | 30787 ms | 42K |
| RAG | C | Tight fit | 7.4 tok/s | 47365 ms | 42K |
How Phi 4 reasoning vision 15B (15B params) fits at each quantization level on MacBook Air M3 24GB (17.3 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 5.9 GB | Low | C49 |
Q3_K_S | 3 | 7.4 GB | Low | C50 |
NVFP4 | 4 | 8.4 GB | Medium | C51 |
Q4_K_M | 4 | 9.2 GB | Medium | C51 |
Q5_K_M | 5 | 10.8 GB | High | C51 |
Q6_KBest for your GPU | 6 | 12.3 GB | High | C50 |
Q8_0 | 8 | 16.1 GB | Very High | F0 |
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 startOpciones de mejora
Añade margen de memoria para más contexto y para que el modelo envejezca mejor.
~$799 MSRP
Añade margen de memoria para más contexto y para que el modelo envejezca mejor.
~$1,099 MSRP
Sube la velocidad estimada de decodificación alrededor de un 243%.
Añade margen de memoria para más contexto y para que el modelo envejezca mejor.
~$1,999 MSRP
Yes, MacBook Air M3 24GB can run Phi 4 reasoning vision 15B with a C grade (Tight fit). Expected decode speed: 7.4 tok/s.
Phi 4 reasoning vision 15B (15B parameters) requires approximately 14.4 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 Air M3 24GB, Phi 4 reasoning vision 15B achieves approximately 7.4 tokens per second decode speed with a time-to-first-token of 26051ms using Q4_K_M quantization.
For coding workloads, Phi 4 reasoning vision 15B on MacBook Air M3 24GB receives a C grade with 7.4 tok/s and 42K context.
On MacBook Air M3 24GB, Phi 4 reasoning vision 15B can safely use up to 42K tokens of context. The model's official context limit is —, but available memory constrains the safe maximum.
Prioritize bandwidth, not only capacity. If this workload feels slow, the next useful step is often a GPU tier with materially faster memory bandwidth rather than only a small bump in capacity.
Not always. MacBook Air M3 24GB 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-m3-air-24gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview: