Phi-4-reasoning-plus 14B needs ~15.5 GB VRAM. MacBook Air M4 24GB has 17.3 GB. With Q4_K_M quantization, expect ~9 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
9.4 tok/s
TTFT
20521 ms
Safe context
25K
Memory
15.5 GB / 17.3 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 | S | Runs well | 9.4 tok/s | 11193 ms | 25K |
| Coding | S | Tight fit | 9.4 tok/s | 20521 ms | 25K |
| Agentic Coding | A | Runs with offload (needs ~0.6 GB host RAM) | 8.3 tok/s | 33839 ms | 25K |
| Reasoning | S | Tight fit | 9.4 tok/s | 24253 ms | 25K |
| RAG | A | Runs with offload (needs ~0.6 GB host RAM) | 8.3 tok/s | 42299 ms | 25K |
Inference speed
Estimated decode speed (tokens/sec) for Phi-4-reasoning-plus 14B at Q4_K_M across popular GPUs and Apple Silicon, using the fastest local runtime per device. Fastest is RTX 5090 32GB at ~144 tok/s. Speed is memory-bandwidth bound, so cards that fit the whole model in VRAM run far faster than ones that offload to system RAM.
| GPU / Mac | Memory | Quant | Speed (tok/s) | Fits? |
|---|---|---|---|---|
 RTX 5090 32GB | 32 GB | Q4_K_M | 143.9 | Fits |
| RTX 4090 24GB | 24 GB | Q4_K_M | 91.8 | Fits |
RX 7900 XTX 24GB | 24 GB | Q4_K_M | 82.9 | Fits |
| RTX 3090 24GB | 24 GB | Q4_K_M | 78.5 | Fits |
| RTX 4080 Super 16GB | 16 GB | Q4_K_M | 75.5 | Tight |
Mac Studio M3 Ultra 256GB | 256 GB | Q4_K_M | 66.8 | Fits |
Mac Studio M2 Ultra 128GB | 128 GB | Q4_K_M | 55.6 | Fits |
Mac Studio M1 Ultra 128GB | 128 GB | Q4_K_M | 52.7 | Fits |
MacBook Pro M4 Max 128GB | 128 GB | Q4_K_M | 37.6 | Fits |
MacBook Pro M4 Max 64GB | 64 GB | Q4_K_M | 37.6 | Fits |
MacBook Pro M3 Max 64GB | 64 GB | Q4_K_M | 28.8 | Fits |
MacBook Pro M1 Max 64GB | 64 GB | Q4_K_M | 26.4 | Fits |
| RTX 4070 12GB | 12 GB | Q4_K_M | 24.9 | Heavy offload |
MacBook Pro M4 Pro 48GB | 48 GB | Q4_K_M | 23.0 | Fits |
| RTX 3060 12GB | 12 GB | Q4_K_M | 14.6 | Heavy offload |
| RTX 4060 8GB | 8 GB | Q4_K_M | 5.5 | Too big |
Estimates for single-stream decoding at Q4_K_M; real tokens/sec varies with prompt length, context, batch size, and runtime build. Prompt processing (prefill) is faster than the decode figures shown here.
How Phi-4-reasoning-plus 14B (14.699999809265137B params) fits at each quantization level on MacBook Air M4 24GB (17.3 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 5.7 GB | Low | S88 |
Q3_K_S | 3 | 7.2 GB | Low | S90 |
NVFP4 | 4 | 8.2 GB | Medium | S91 |
Q4_K_M | 4 | 9.0 GB | Medium | S91 |
Q5_K_M | 5 | 10.6 GB | High | S91 |
Q6_KBest for your GPU | 6 | 12.1 GB | High | S90 |
Q8_0 | 8 | 15.7 GB | Very High | F0 |
F16 | 16 | 30.1 GB | Maximum | F0 |
Copy-paste commands to run Phi-4-reasoning-plus 14B on your machine.
Run
ollama run phi4-reasoningYour hardware
| Model | Params | Grade | Decode | Capabilities |
|---|---|---|---|---|
 Magistral Small 2507 | 24B | A | 7.3 tok/s | |
| Devstral Small 2 24B Instruct | 24B | A | 7.3 tok/s |
Yes, MacBook Air M4 24GB can run Phi-4-reasoning-plus 14B with a S grade (Tight fit). Expected decode speed: 9.4 tok/s.
Phi-4-reasoning-plus 14B (14.699999809265137B parameters) requires approximately 15.5 GB of memory with Q4_K_M quantization.
The recommended quantization for Phi-4-reasoning-plus 14B is Q4_K_M, which balances quality and memory efficiency.
On MacBook Air M4 24GB, Phi-4-reasoning-plus 14B achieves approximately 9.4 tokens per second decode speed with a time-to-first-token of 20521ms using Q4_K_M quantization.
For coding workloads, Phi-4-reasoning-plus 14B on MacBook Air M4 24GB receives a S grade with 9.4 tok/s and 25K context.
On MacBook Air M4 24GB, Phi-4-reasoning-plus 14B can safely use up to 25K tokens of context. The model's official context limit is 33K, but available memory constrains the safe maximum.
Not always. MacBook Air M4 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/phi-4-reasoning-plus-14b-on-m4-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: