Phi-4 · Mini
Phi-4 Mini completed both matched CPU servers. Its full-Vulkan window coincided with an i915 GPU hang.
Phi-4 Mini completed both matched CPU servers. Its full-Vulkan window coincided with an i915 GPU hang.
It provides a second model family inside the matched runtime result and a retained failure outside the clean Vulkan pair.
The rows on this page use Q4_K_M through llama.cpp 9a286ac and Ollama 0.32.1. They describe those exact artifacts and runs, not every version that shares the model name.
The fastest retained generation row is 2.072 tok/s through Ollama 0.32.1 using CPU in Matched server request mode. Ollama reported 32.00% higher internal generation throughput than the paired llama.cpp row.
1 retained row is a failure: The run window contained an i915 GPU hang even though llama-bench returned zero. The kernel event overrides the process exit code.
The rows below can come from different prompts and methods. Open the full test before treating two numbers as a direct comparison.
| Model and artifact | Runtime and mode | Generation | Prompt | Peak | State | Full test |
|---|---|---|---|---|---|---|
| Phi-4 Mini Q4_K_M | llama.cpp 9a286ac CPU · Matched server request | 1.57 tok/s | 2.115 tok/s | 82 °C | Published result | Matched CPU runtimes |
Open result detailsWhy this model is herePhi-4 Mini completed both matched CPU servers. Its full-Vulkan window coincided with an i915 GPU hang. It provides a second model family inside the matched runtime result and a retained failure outside the clean Vulkan pair. What ranQ4_K_M ran through llama.cpp 9a286ac using CPU in Matched server request mode on Youyeetoo X1S. Three measured requests completed with a clean kernel window. Recorded setup
Artifact SHA-256 | ||||||
| Phi-4 Mini Q4_K_M | Ollama 0.32.1 CPU · Matched server request | 2.072 tok/s | 3.131 tok/s | 82 °C | Published result | Matched CPU runtimes |
Open result detailsWhy this model is herePhi-4 Mini completed both matched CPU servers. Its full-Vulkan window coincided with an i915 GPU hang. It provides a second model family inside the matched runtime result and a retained failure outside the clean Vulkan pair. What ranQ4_K_M ran through Ollama 0.32.1 using CPU in Matched server request mode on Youyeetoo X1S. Ollama reported 32.00% higher internal generation throughput than the paired llama.cpp row. Recorded setup
Artifact SHA-256 | ||||||
| Phi-4 Mini Q4_K_M | llama.cpp 9a286ac Vulkan · Full Vulkan | n/a | n/a | n/a | Failed run | CPU and Vulkan modes |
Open result detailsWhy this model is herePhi-4 Mini completed both matched CPU servers. Its full-Vulkan window coincided with an i915 GPU hang. It provides a second model family inside the matched runtime result and a retained failure outside the clean Vulkan pair. What ranQ4_K_M ran through llama.cpp 9a286ac using Vulkan in Full Vulkan mode on Youyeetoo X1S. The run window contained an i915 GPU hang even though llama-bench returned zero. The kernel event overrides the process exit code. Recorded setupThe full test page contains the shared controls and comparison boundary for this row. | ||||||
| Phi-4 Mini Q4_K_M | Ollama 0.32.1 CPU · Mean warm generation | 1.991 tok/s | n/a | 77 °C | Published result | Original CPU matrix |
Open result detailsWhy this model is herePhi-4 Mini completed both matched CPU servers. Its full-Vulkan window coincided with an i915 GPU hang. It provides a second model family inside the matched runtime result and a retained failure outside the clean Vulkan pair. What ranQ4_K_M ran through Ollama 0.32.1 using CPU in Mean warm generation mode on Youyeetoo X1S. Patient local batch use. Recorded setupThe full test page contains the shared controls and comparison boundary for this row. | ||||||
2026-08-31
Internal generation rates are comparable inside this eight-row test. Model load time was not an identical part of the timed path.
Open full test2026-08-31
Compare the clean Qwen rows inside this group. The larger-model entries are failure outcomes, not performance rows.
Open full test2026-08-23
These warm Ollama results belong together. They should not be used as the other half of the later llama-bench runtime comparison.
Open full test