Phi-4 14B

14B

Microsoft Phi

Microsoft Phi-4 dense 14B — strong reasoning for size. Q4 ~9GB fits 12GB cards with moderate context.

⬇ 10.8K HF downloads♥ 62 likesbartowski/phi-4-GGUF· stats from 7/27/2026
Consumer GPUMac / Apple Silicon

16K

Max Context

3

Quant Variants

GGUF Q5_K_M

Best Quality

98.7%

Accuracy Retained

Calculate VRAMHugging FaceCompare

Quantization Variants

Per-quant VRAM, quality loss, and inference speed on RTX 4090

Measured = site benchmarks · Estimated = formula · Community = public reports

FormatLevelBPWVRAMPPL LossSpeedSourceActions
GGUFQ4_K_M4.859.1 GB2.7%88 tok/sCommunity
CalcHF
GGUFQ5_K_M5.6810.5 GB1.3%78 tok/sEstimated
CalcHF
AWQINT448.2 GB3.6%112 tok/sEstimated
CalcHF

Similar models

Compare with Phi-3 Medium
14B

Phi-3 Medium 14B Instruct

Microsoft Phi

Consumer GPUMac / Apple Silicon
8.8 GBmin VRAM·99.2%accuracy

Microsoft's mid-size Phi-3. Excellent quality-per-GB on 16GB cards.

3.8B

Phi-4 Mini Instruct

Microsoft Phi

Consumer GPUMac / Apple Silicon
2.5 GBmin VRAM·99.8%accuracy

Latest Phi mini with improved math and code. Strong 4B-class performer.

3.8B

Phi-3.5 Mini Instruct

Microsoft Phi

Consumer GPUMac / Apple Silicon
2.5 GBmin VRAM·99.8%accuracy

Microsoft's tiny powerhouse. Best 4B model for on-device deployment.

14B

Qwen2.5 14B Instruct

Alibaba Qwen2.5

Consumer GPUMac / Apple Silicon
9.2 GBmin VRAM·98.6%accuracy

The sweet spot between performance and resource usage. 16GB VRAM with Q4.