/hub/runs/x1s-runtime-compatibility
Published result2026-08-31Youyeetoo X1S

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.

Recorded results

Open the details under any row for the specific setup, outcome, artifact identity, and supporting file.

Model and artifactRuntime and modeGenerationPromptPeakState
BitCPM-CANN 1B
Official TQ2_0 GGUF
llama.cpp 9a286ac
CPU · True CPU, five repetitions
8.584 tok/s13.01 tok/s76 °CPublished result
Open result details

Why this model is here

The 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 ran

Official 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

Threads
4
Prompt
128 tokens
Output
96 tokens
Batch
512 / 512 microbatch
Measured runs
5
Generation stddev
0.029317
Thermal ceiling
85 °C

Artifact SHA-2562394c15cbea2181b72bfb4215d8417d8d1f2f6214069da2d01fde32ce3b13fce

BitCPM-CANN 1B
Official TQ2_0 GGUF
Ollama 0.32.1
CPU · Model load
n/an/an/aFailed run
Open result details

Why this model is here

The 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 ran

Official 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 setup

The full test page contains the shared controls and comparison boundary for this row.

Artifact SHA-2562394c15cbea2181b72bfb4215d8417d8d1f2f6214069da2d01fde32ce3b13fce

Gemma 3 4B
Separate text-only derivative
llama.cpp 9a286ac
CPU · True CPU, five repetitions
1.624 tok/s2.172 tok/s81 °CPublished result
Open result details

Why this model is here

A 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 ran

Separate 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

Threads
4
Prompt
128 tokens
Output
96 tokens
Batch
512 / 512 microbatch
Measured runs
5
Generation stddev
0.003291
Thermal ceiling
85 °C

Artifact SHA-256510408e8043ca1c741fe9a16088d47e8fa0d016033c6acf0c50c50c7c93b6530

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.

© 2026 Trevor Unland. All rights reserved.

RSS Feed

$ echo "Built with React + TypeScript"