Phi 3 Medium 14B needs ~14.9 GB VRAM. Intel Arc Pro B60 24GB has 24.0 GB. With Q4_K_M quantization, expect ~31 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
31.0 tok/s
TTFT
6246 ms
Safe context
64K
Memory
14.9 GB / 24.0 GB
The raw memory story may look fine, but the software ecosystem is still a constraint here.
Runtime ecosystem is narrower than CUDA
Intel GPUs can look attractive on memory per dollar, but local AI tooling, kernels, and model coverage are still broader and easier on CUDA today.
Prefer CUDA if you want the path of least resistance
If your goal is maximum runtime coverage, easier troubleshooting, and better support for new local AI releases, CUDA is usually still the safer upgrade path.
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | B | Runs well | 31.0 tok/s | 3407 ms | 64K |
| Coding | B | Runs well | 31.0 tok/s | 6246 ms | 64K |
| Agentic Coding | B | Runs well | 31.0 tok/s | 9085 ms | 64K |
| Reasoning | B | Runs well | 31.0 tok/s | 7382 ms | 64K |
| RAG | B | Runs well | 31.0 tok/s | 11356 ms | 64K |
Inference speed
Estimated decode speed (tokens/sec) for Phi 3 Medium 14B at Q4_K_M across popular GPUs and Apple Silicon, using the fastest local runtime per device. Fastest is RTX 5090 32GB at ~151 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 | 151.1 | Fits |
| RTX 4090 24GB | 24 GB | Q4_K_M | 96.4 | Fits |
RX 7900 XTX 24GB | 24 GB | Q4_K_M | 87.0 | Fits |
| RTX 3090 24GB | 24 GB | Q4_K_M | 82.5 | Fits |
| RTX 4080 Super 16GB | 16 GB | Q4_K_M | 80.7 | Tight |
Mac Studio M3 Ultra 256GB | 256 GB | Q4_K_M | 70.1 | Fits |
Mac Studio M2 Ultra 128GB | 128 GB | Q4_K_M | 58.4 | Fits |
Mac Studio M1 Ultra 128GB | 128 GB | Q4_K_M | 55.4 | Fits |
MacBook Pro M4 Max 128GB | 128 GB | Q4_K_M | 38.1 | Fits |
MacBook Pro M4 Max 64GB | 64 GB | Q4_K_M | 38.1 | Fits |
MacBook Pro M3 Max 64GB | 64 GB | Q4_K_M | 30.2 | Fits |
| RTX 4070 12GB | 12 GB | Q4_K_M | 28.4 | Heavy offload |
MacBook Pro M1 Max 64GB | 64 GB | Q4_K_M | 27.7 | Fits |
MacBook Pro M4 Pro 48GB | 48 GB | Q4_K_M | 23.3 | Fits |
| RTX 3060 12GB | 12 GB | Q4_K_M | 16.7 | Heavy offload |
| RTX 4060 8GB | 8 GB | Q4_K_M | 6.1 | 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 3 Medium 14B (14B params) fits at each quantization level on Intel Arc Pro B60 24GB (24.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 5.5 GB | Low | B57 |
Q3_K_S | 3 | 6.9 GB | Low | B58 |
NVFP4 | 4 | 7.8 GB | Medium | B58 |
Q4_K_M | 4 | 8.5 GB | Medium | B59 |
Q5_K_M | 5 | 10.1 GB | High | B60 |
Q6_K | 6 | 11.5 GB | High | B61 |
Q8_0Best for your GPU | 8 | 15.0 GB | Very High | B61 |
F16 | 16 | 28.7 GB | Maximum | F0 |
Copy-paste commands to run Phi 3 Medium 14B on your machine.
Run
ollama run phi3:mediumOpções de upgrade
RTX 5090 32GBOpção econômicaRaises estimated decode speed by about 373%.
Adds memory headroom for longer context windows and future model growth.
This is not only a hardware jump. It also gives you a cleaner runtime ecosystem for local LLM tooling.
~$1,999 MSRP
RTX PRO 4500 Blackwell 32GBMelhor custo-benefícioRaises estimated decode speed by about 205%.
Adds memory headroom for longer context windows and future model growth.
This is not only a hardware jump. It also gives you a cleaner runtime ecosystem for local LLM tooling.
~$2,499 MSRP
Yes, Intel Arc Pro B60 24GB can run Phi 3 Medium 14B with a B grade (Runs well). Expected decode speed: 31.0 tok/s.
Phi 3 Medium 14B (14B parameters) requires approximately 14.9 GB of memory with Q4_K_M quantization.
The recommended quantization for Phi 3 Medium 14B is Q4_K_M, which balances quality and memory efficiency.
On Intel Arc Pro B60 24GB, Phi 3 Medium 14B achieves approximately 31.0 tokens per second decode speed with a time-to-first-token of 6246ms using Q4_K_M quantization.
For coding workloads, Phi 3 Medium 14B on Intel Arc Pro B60 24GB receives a B grade with 31.0 tok/s and 64K context.
On Intel Arc Pro B60 24GB, Phi 3 Medium 14B can safely use up to 64K tokens of context. The model's official context limit is 128K, but available memory constrains the safe maximum.
Prefer CUDA if you want the path of least resistance. If your goal is maximum runtime coverage, easier troubleshooting, and better support for new local AI releases, CUDA is usually still the safer upgrade path.
Often yes, if your goal is the easiest setup and the widest runtime support. Intel can offer attractive memory capacity, but CUDA still tends to win on tooling maturity, guides, kernels, and model coverage for local AI.
Paste this snippet into any page to show a live fit card.
<iframe src="https://willitrunai.com/embed/phi-3-medium-14b-on-arc-pro-b60-24gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview: