optimum-intel-internal-testing/tiny-random-phi-4-multimodalFP32vllmderived by optimum-intel-internal-testing
hf.co/unsloth/Phi-4-mini-reasoning-GGUF:IQ1_SIQ1_Sollamameasured herequantized by unsloth
hf.co/unsloth/Phi-4-mini-reasoning-GGUF:IQ2_XXSIQ2_XXSollamaquantized by unsloth
hf.co/unsloth/Phi-4-mini-reasoning-GGUF:IQ3_XXSIQ3_XXSollamameasured herequantized by unsloth
hf.co/unsloth/Phi-4-mini-instruct-GGUF:Q2_K_LQ2_K_Lollamaquantized by unsloth
hf.co/unsloth/Phi-4-mini-instruct-GGUF:Q2_KQ2_Kollamameasured herequantized by unsloth
hf.co/unsloth/Phi-4-mini-instruct-GGUF:Q3_K_MQ3_K_Mollamameasured herequantized by unsloth
mlx-community/Phi-4-mini-instruct-4bit4BITmlxquantized by mlx-community
lmstudio-community/Phi-4-mini-reasoning-MLX-4bit4BITmlxquantized by lmstudio-community
charakaweb/phi4-clinical-mlx4BITmlxderived by charakaweb
hf.co/bartowski/microsoft_Phi-4-mini-instruct-GGUF:IQ4_XSIQ4_XSollamameasured herequantized by bartowski
hf.co/unsloth/Phi-4-mini-reasoning-GGUF:Q4_0Q4_0ollamaquantized by unsloth
hf.co/unsloth/Phi-4-mini-instruct-GGUF:Q4_K_MQ4_K_Mollamameasured herequantized by unsloth
hf.co/unsloth/Phi-4-mini-reasoning-GGUF:Q4_K_MQ4_K_Mollamameasured herequantized by unsloth
hf.co/unsloth/Phi-4-mini-instruct-GGUF:Q5_K_MQ5_K_Mollamameasured herequantized by unsloth
mlx-community/Phi-4-mini-instruct-6bit6BITmlxquantized by mlx-community
unsloth/Phi-4-mini-instruct-unsloth-bnb-4bitBITSANDBYTESvllmderived by unsloth
hf.co/unsloth/Phi-4-reasoning-plus-GGUF:IQ1_SIQ1_Sollamaquantized by unsloth
mlx-community/Phi-4-mini-instruct-8bit8BITmlxquantized by mlx-community
hf.co/unsloth/Phi-4-mini-instruct-GGUF:Q8_0Q8_0ollamameasured herequantized by unsloth
hf.co/unsloth/Phi-4-mini-reasoning-GGUF:Q8_0Q8_0ollamaquantized by unsloth
hf.co/unsloth/Phi-4-reasoning-plus-GGUF:IQ2_XXSIQ2_XXSollamaquantized by unsloth
hf.co/microsoft/phi-4-gguf:Q2_KQ2_Kollamapublished by microsoft
hf.co/unsloth/Phi-4-reasoning-plus-GGUF:IQ3_XXSIQ3_XXSollamaquantized by unsloth
hf.co/microsoft/phi-4-gguf:IQ3_XXSIQ3_XXSollamapublished by microsoft
hf.co/microsoft/phi-4-gguf:IQ3_SIQ3_Sollamapublished by microsoft
microsoft/Phi-4-mini-instructBF16vllmmeasured herepublished by microsoft
microsoft/Phi-4-mini-reasoningBF16vllmpublished by microsoft
unsloth/Phi-4-mini-instructBF16vllmderived by unsloth
hf.co/unsloth/Phi-4-mini-instruct-GGUF:BF16BF16ollamameasured herequantized by unsloth
hf.co/unsloth/Phi-4-mini-reasoning-GGUF:BF16BF16ollamaquantized by unsloth
microsoft/Phi-4-mini-flash-reasoningBF16vllmpublished by microsoft
mlx-community/phi-4-4bit4BITmlxquantized by mlx-community
lmstudio-community/Phi-4-reasoning-MLX-4bit4BITmlxquantized by lmstudio-community
lmstudio-community/Phi-4-reasoning-plus-MLX-4bit4BITmlxquantized by lmstudio-community
hf.co/microsoft/phi-4-gguf:Q4_0Q4_0ollamapublished by microsoft
hf.co/unsloth/Phi-4-reasoning-plus-GGUF:Q4_0Q4_0ollamaquantized by unsloth
hf.co/MaziyarPanahi/phi-4-GGUF:Q4_K_MQ4_K_Mollamaquantized by MaziyarPanahi
hf.co/unsloth/Phi-4-reasoning-plus-GGUF:Q4_K_MQ4_K_Mollamameasured herequantized by unsloth
microsoft/Phi-4-multimodal-instructBF16vllmpublished by microsoft
mlx-community/phi-4-8bit8BITmlxquantized by mlx-community
hf.co/microsoft/phi-4-gguf:Q8_0Q8_0ollamapublished by microsoft
hf.co/unsloth/Phi-4-reasoning-plus-GGUF:Q8_0Q8_0ollamaquantized by unsloth
RedHatAI/phi-4-FP8-dynamicFP8vllmquantized by RedHatAI
microsoft/paza-Phi-4-multimodal-instructFP32vllmpublished by microsoft
microsoft/Phi-4-reasoningBF16vllmpublished by microsoft
microsoft/Phi-4-reasoning-plusBF16vllmpublished by microsoft
hf.co/microsoft/phi-4-gguf:BF16BF16ollamameasured herepublished by microsoft
hf.co/unsloth/Phi-4-reasoning-plus-GGUF:BF16BF16ollamaquantized by unsloth
microsoft/Phi-4-reasoning-vision-15BBF16vllmpublished by microsoft
bartowski/phi-4-GGUF:F32F32llamacppquantized by bartowski
Sizes are what the catalog declares, not what a machine measured — fitting on disk is necessary and not sufficient. Nobody here has run these on your machine, and this narrows the candidates rather than certifying one.