Phi-4 14B

At the default Q4_K_M, 59 of 140 phones have enough estimated usable memory; 59 also reach 3+ tokens/s. On Mac, 52 of 54 exact configurations pass using that quant or a smaller tracked fallback.

Params
14.7B
Family
phi
Released
2024-12
Tags
chat · reasoning

Downloads & memory by quant

The download is only the weights — add KV cache and runtime to get what your phone actually needs. “Memory-fit” only means it can load; “usable” also requires an estimated 3+ tokens/s. Each row uses that row's quant. ★ = recommended.

QuantDownloadMemory neededPhone reality
Q2_K5.5 GB~7.4 GB105 memory-fit · 89 usable
Q3_K_M7.4 GB~9.4 GB59 memory-fit · 59 usable
IQ4_XS7.9 GB~9.9 GB59 memory-fit · 59 usable
Q4_08.4 GB~10.4 GB59 memory-fit · 59 usable
Q4_K_S8.4 GB~10.4 GB59 memory-fit · 59 usable
Q4_K_M9.1 GB~11.2 GB59 memory-fit · 59 usable
Q5_K_M10.6 GB~12.8 GB4 memory-fit · 4 usable
Q6_K12 GB~14.2 GB4 memory-fit · 0 usable
Q8_015.6 GB~18 GB3 memory-fit · 0 usable

Phi-4 14B at Q4_K_M on 140 phones

This table is fixed to the recommended Q4_K_M, on each phone's largest RAM option. Counts for smaller quants above will differ. All phones are shown, sorted by fit and estimated experience; tap one for the full report.

PhoneChip · RAMNeedsSpeedVerdict

~ = bandwidth-based estimate · ✓ = measured on real hardware

Phi-4 14B on 54 Mac configurations

Each Mac uses the recommended Q4_K_M at 4K context when it fits, or the largest smaller tracked quant that fits. Each row links to the full report with a macOS-specific setup guide.

MacUnified memoryQuantWorking budgetNeedsEstimated speedVerdict

FAQ

How much RAM do I need to run Phi-4 14B on a phone?

At Q4_K_M, Phi-4 14B needs ~11.2GB of usable memory (weights + KV cache + runtime). In practice that means a 16GB+ Android phone or a 24GB+ iPhone — iOS lets a single app use less of its RAM than Android does.

How fast does Phi-4 14B run on a flagship phone?

On the OnePlus 13 (Snapdragon 8 Elite) it runs at ~3.8 tokens/s at Q4_K_M, estimated from memory bandwidth. Anything above ~8 tokens/s feels smooth for chat.

Can an iPhone run Phi-4 14B?

Not really: the best iPhone we track (iPhone Air) has ~7.8GB usable, but Phi-4 14B needs 11.2GB at Q4_K_M.

What is the best quantization of Phi-4 14B for mobile?

Q4_K_M (9.1GB download) is the size/quality sweet spot of the 9 quants available. Total memory needed is ~11.2GB once the KV cache and runtime are counted — the download size alone understates it.

How many phones can run Phi-4 14B?

59 of the 140 phones we track have enough estimated usable memory at Q4_K_M; 59 also reach our usable-speed threshold of 3 tokens/s, and 0 run smoothly. Memory-fit alone does not mean a good experience.

Which Macs can run Phi-4 14B?

52 of the 54 exact Mac configurations we track have enough estimated working memory. Each Mac uses the recommended Q4_K_M when it fits, or the largest smaller tracked quant that fits, and separates installed unified memory, the macOS reserve, and estimated speed.

What is Phi-4 14B good for on a phone?

It's tagged for chat, reasoning. At 14.7B parameters, it prioritizes answer quality over speed — expect slower decoding.

Similar models

Phi-4 Mini 3.8BQwen3 14BMinistral 3 14BGemma 3 12BGemma 4 12B