Qwen3 · 4B
The Q4_K_M file completed the matched CPU test, then reached an i915 reset timeout during full Vulkan.
The Q4_K_M file completed the matched CPU test, then reached an i915 reset timeout during full Vulkan.
It marks the point where the clean small-model Vulkan result stopped scaling into a reliable larger-model run on this software stack.
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 2.002 tok/s through Ollama 0.32.1 using CPU in Matched server request mode. Ollama reported 34.89% higher internal generation throughput than the paired llama.cpp row.
1 retained row is a failure: The run reached an i915 reset timeout. No speed score is published for it.
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 |
|---|---|---|---|---|---|---|
| Qwen3 4B Instruct Q4_K_M | llama.cpp 9a286ac CPU · Matched server request | 1.484 tok/s | 1.899 tok/s | 81 °C | Published result | Matched CPU runtimes |
Open result detailsWhy this model is hereThe Q4_K_M file completed the matched CPU test, then reached an i915 reset timeout during full Vulkan. It marks the point where the clean small-model Vulkan result stopped scaling into a reliable larger-model run on this software stack. 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 | ||||||
| Qwen3 4B Instruct Q4_K_M | Ollama 0.32.1 CPU · Matched server request | 2.002 tok/s | 2.789 tok/s | 81 °C | Published result | Matched CPU runtimes |
Open result detailsWhy this model is hereThe Q4_K_M file completed the matched CPU test, then reached an i915 reset timeout during full Vulkan. It marks the point where the clean small-model Vulkan result stopped scaling into a reliable larger-model run on this software stack. What ranQ4_K_M ran through Ollama 0.32.1 using CPU in Matched server request mode on Youyeetoo X1S. Ollama reported 34.89% higher internal generation throughput than the paired llama.cpp row. Recorded setup
Artifact SHA-256 | ||||||
| Qwen3 4B 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 hereThe Q4_K_M file completed the matched CPU test, then reached an i915 reset timeout during full Vulkan. It marks the point where the clean small-model Vulkan result stopped scaling into a reliable larger-model run on this software stack. What ranQ4_K_M ran through llama.cpp 9a286ac using Vulkan in Full Vulkan mode on Youyeetoo X1S. The run reached an i915 reset timeout. No speed score is published for it. Recorded setupThe full test page contains the shared controls and comparison boundary for this row. | ||||||
| Qwen3 4B Instruct Q4_K_M | Ollama 0.32.1 CPU · Mean warm generation | 1.824 tok/s | n/a | 77 °C | Published result | Original CPU matrix |
Open result detailsWhy this model is hereThe Q4_K_M file completed the matched CPU test, then reached an i915 reset timeout during full Vulkan. It marks the point where the clean small-model Vulkan result stopped scaling into a reliable larger-model run on this software stack. 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