- quant:
- 4bit
agenticcoding
User currently runs Qwen3.6-35B-A3B-4bit on M3 Max 128GB for production sub-agent delegations. Also mentions GLM-5.1 for orchestration. Considering building a 5090 rig.
M3 Max 128GB
APPLE · 128GB unified memory · 2 reports
This page is thin (2 of 3 reports needed for indexing). Help fill it in.
Qwen3.6 27B
M3 Max 128GB · MLX · 290,000 ctx
- throughput:
- 5.5 t/s gen · 160.0 t/s pp
- quant:
- Q8 (mlx)
long-context
User reports 160 tok/s prefill, 5-6 tok/s generation on M5 Max 128GB with Qwen 3.6 27B Q8 MLX at 290k context. GPU utilization only 36-50%, feels off compared to expected 8-14 tok/s generation. Asks for comparison with other setups.