[tarruda]

If your framework desktop is the 128G Strix Halo, I recommend giving Qwen 3.5 122B-A10B a shot.

This Q5_K_M quant should be near lossless and fit with full 256K context in about 100GB of RAM: https://huggingface.co/AesSedai/Qwen3.5-122B-A10B-GGUF

[Catloafdev]

3.6 scores better on coding across the board.

Edit: specifically Qwen 3.6 27B beats that on coding and agentic workflows.

[tarruda]

Vibe thinker also beats Opus 4.5

[bakies]

I'll keep this in mind.