Gemma 4 12B aced the short jobs, but its code review still needed a red pen
Ollama Gemma 4 12B passed all six scorer-v2 workflow cases, then mixed four useful code-review findings with nine that needed qualification or rejection.
Ollama Gemma 4 12B passed all six scorer-v2 workflow cases, then mixed four useful code-review findings with nine that needed qualification or rejection.
A real-workflow qualification of Ollama Qwen 3.5 0.8B: three of six bounded cases passed, and all four code-review recommendations were false or materially wrong.
A real-workflow qualification of oMLX Llama 3.3 70B: four of six bounded cases passed, but request failures and invalid output prevented a fair repository-review judgment.
A real-workflow qualification of oMLX Qwen 3.6 35B-A3B: four domain passes out of six, excellent latency, and useful but supervision-heavy review output.
A real-workflow qualification of oMLX Qwen 3.5 35B-A3B: exceptional local speed, three domain passes out of six, and weak broad-review precision.
A real-workflow qualification of oMLX Qwen 3.5 9B: very fast short calls, two domain passes out of six, and too many confident code-review errors.
A real-workflow qualification of oMLX Qwen 3.5 4B: fast bounded work, repetitive repository review, and an 82.8 percent false-or-materially-wrong rate after source adjudication.
A real-workflow qualification of oMLX Qwen 3.8 27B 8-bit: strong bounded work, useful code-review leads, and a costly false-positive problem.
I expected this test to end with a speed chart. It ended with a subtraction problem. The subject was Qwen 3.8 27B on a 64 GB M5 Max, served two ways: Ollama 0.34.4 and oMLX 0.7.0rc1. I wanted two answers that are easy to blur together. First, which serving engine handles the closest practical 4-bit…
Somewhere on a shelf in a quiet house, a small gray box is doing something almost impossible: it is awake. Not the kind of awake that needs coffee, not the kind that checks the time out of the corner of its eye and decides the night is long enough. It is the kind of awake…