Qwen3.5 · 9B
The official Q4_K_M Ollama artifact fit in 16 GB and averaged 1.110 tok/s across five prompts.
The official Q4_K_M Ollama artifact fit in 16 GB and averaged 1.110 tok/s across five prompts.
This was a fit-and-completion test for a much larger model on the X1S, not a claim that 1.110 tok/s is comfortable interactive speed.
The rows on this page use Q4_K_M through 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 1.11 tok/s through Ollama 0.32.1 using CPU in Five-prompt average mode. The 9B artifact fit in 16 GB and completed five prompts, but generation requires patience.
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 |
|---|---|---|---|---|---|---|
| Qwen3.5 9B Q4_K_M | Ollama 0.32.1 CPU · Five-prompt average | 1.11 tok/s | n/a | 82 °C | Published result | Additional models |
Open result detailsWhy this model is hereThe official Q4_K_M Ollama artifact fit in 16 GB and averaged 1.110 tok/s across five prompts. This was a fit-and-completion test for a much larger model on the X1S, not a claim that 1.110 tok/s is comfortable interactive speed. What ranQ4_K_M ran through Ollama 0.32.1 using CPU in Five-prompt average mode on Youyeetoo X1S. The 9B artifact fit in 16 GB and completed five prompts, but generation requires patience. Recorded setup
Artifact SHA-256 | ||||||
2026-08-31
The rows use different repetition counts and artifact states. They are useful operating points, not one controlled model-quality contest.
Open full test