BitCPM and Gemma Runtime Compatibility
The exact BitCPM TQ2_0 file exposed a runtime-support difference. A separate Gemma 3 text-only derivative documented a different conversion problem before the later Vulkan failure.
This page keeps the shared controls, retained measurements, failures, and comparison limits together. The linked files are there when you need the underlying table or method.
Comparison boundary
BitCPM is not a matched runtime speed contest because Ollama never loaded the model. The Gemma derivative is inspectable but does not repair the Vulkan device-loss path.
Related pages
Recorded results
Open the details under any row for the specific setup, outcome, artifact identity, and supporting file.
| Model and artifact | Runtime and mode | Generation | Prompt | Peak | State |
|---|---|---|---|---|---|
| BitCPM-CANN 1B Official TQ2_0 GGUF | llama.cpp 9a286ac CPU · True CPU, five repetitions | 8.584 tok/s | 13.01 tok/s | 76 °C | Published result |
Open result detailsWhy this model is hereThe exact official TQ2_0 GGUF ran in pinned llama.cpp and failed to load in Ollama 0.32.1. This is a runtime-support result, not a speed contest. The same verified file produced inference in one runtime and a tensor-size overflow in the other. What ranOfficial TQ2_0 GGUF ran through llama.cpp 9a286ac using CPU in True CPU, five repetitions mode on Youyeetoo X1S. Pinned llama.cpp accepted the verified file and completed the controlled true-CPU workload. Recorded setup
Artifact SHA-256 | |||||
| BitCPM-CANN 1B Official TQ2_0 GGUF | Ollama 0.32.1 CPU · Model load | n/a | n/a | n/a | Failed run |
Open result detailsWhy this model is hereThe exact official TQ2_0 GGUF ran in pinned llama.cpp and failed to load in Ollama 0.32.1. This is a runtime-support result, not a speed contest. The same verified file produced inference in one runtime and a tensor-size overflow in the other. What ranOfficial TQ2_0 GGUF ran through Ollama 0.32.1 using CPU in Model load mode on Youyeetoo X1S. Ollama rejected the same verified file with a tensor-size overflow before inference. Recorded setupThe full test page contains the shared controls and comparison boundary for this row. Artifact SHA-256 | |||||
| Gemma 3 4B Separate text-only derivative | llama.cpp 9a286ac CPU · True CPU, five repetitions | 1.624 tok/s | 2.172 tok/s | 81 °C | Published result |
Open result detailsWhy this model is hereA separate text-only derivative completed true CPU. The later Vulkan path ended with timeouts, an i915 reset, and device loss. It records two different compatibility boundaries: converting the older multimodal artifact for current llama.cpp and the separate Vulkan failure that conversion did not fix. What ranSeparate text-only derivative ran through llama.cpp 9a286ac using CPU in True CPU, five repetitions mode on Youyeetoo X1S. The derived copy completed true CPU. The original multimodal source artifact was not overwritten. Recorded setup
Artifact SHA-256 | |||||
Supporting evidence
Results and method
These are the few files that support this page directly. The repository holds the wider project history.
Controls
- Official BitCPM-CANN 1B TQ2_0 GGUF
- Pinned llama.cpp true-CPU path
- Ollama 0.32.1 load attempt
- Gemma source artifact preserved
- Patch created a separate text-only derivative
What this run established
- $llama.cpp ran BitCPM at 8.584 generation tok/s.
- $Ollama rejected the same verified file with a tensor-size overflow.
- $The Gemma derivative completed true CPU, then the separate Vulkan path still failed.