amanwalksdownthestreet/Qwen3-Coder-30B-A3B-Instruct-exl3

ExLlamaV3 quantizations of Qwen3-Coder-30B-A3B-Instruct with tensor-level (L3) optimization and boosted attention layers (5-6 bit). Maximum effort applied towards the goal of achieving the best possible quantizations at the expense of time and compute.

Using this measurement.json file and the base quants provided, additional highly-optimized quantizations can be made in seconds at any reasonable bpw by anyone. All work done with ExLlamaV3 v0.0.18.

Optimized

VRAM-targeted quants using exl3's measure.py → optimize.py → recompile.py pipeline.

The 4.90bpw quant hit the optimization ceiling - requesting higher bpw (5.30, 6.95) produced identical 4.83bpw pre-boost output, indicating no further beneficial tensor swaps available.

Base