Repository Issue Activity (beta)

#171 Qwen3.8-27B not showing up for multiple reasons

#24 Improve coverage for newer Qwen models and task profiles

#36 Improve Strix Halo / Ryzen AI MAX modeling beyond v0.5.4 heuristics

#83 Benchmark pipeline fails on macOS: AA scraper broken, HF 429s, community GGUF ID mismatch

#158 UnicodeDecodeError: 'charmap' codec can't decode byte 0x8f in position 226335: character maps to <undefined>

#163 Add a specific repo ID with a command

#76 A3000 Laptop 6GB: Recommendations very poor

#160 Non-UTF-8 cache file raises an uncaught UnicodeDecodeError instead of a cache miss

#65 Feature Request: Multi-GPU simulation via --gpu flag (heterogeneous setups)

#1 oMLX vs LLama.ccp

#152 Detect how much of unified memory is available to GPU on Mac

#148 a pytest error (field test)

#155 fix(run): don't resolve recommendations to modified GGUF models

#150 ci: use locked development tools in required checks

#101 Retune AA index normalization and refresh snapshot for AA's reworked index

#93 Does not correctly detect Intel Arc Pro B70 properties

#137 Clicking a result's link opens a different model's page than the one shown in the results.

#127 Add pre-commit config for ruff

#53 brew install

#117 charset error after installation

#104 Results not good for my GPU

#128 Suggest to add HuggingFace's mirror site

#132 Allow manual override of RAM bandwidth and VRAM size for iGPU environments

#135 SSL: CERTIFICATE_VERIFY_FAILED

#107 Substring model search silently returns the wrong size (ask 7B, get 1.7B)