Qwen3.6-35B-A3B optimized for MLX.
- 4-bit baseline with important layers at 8-bit and BF16.
- This quant does not support image input.
I ended up selecting two winners from my trials. This is the quality+ version, and here's the speed+ version.
Usage
# Start server at http://localhost:8080/v1/chat/completions
uvx --from mlx-lm mlx_lm.server \
--host 127.0.0.1 \
--port 8080 \
--model spicyneuron/Qwen3.6-35B-A3B-MLX-5.4bit
Benchmarks
| metric | mlx-community/ Qwen3.6-35B-A3B-4bit | mlx-community/ Qwen3.6-35B-A3B-4.4bit-msq | 4.8 bit | 5.4 bit (this model) |
|---|---|---|---|---|
| bpw | 4.503 | 4.787 | 4.788 | 5.438 |
| peak memory (1024/512) | 20.683 | 21.922 | 21.928 | 24.741 |
| prompt tok/s (1024) | 2719.4470 ± 15.2250 | 2695.9370 ± 12.5260 | 2734.5260 ± 3.8810 | 2665.3060 ± 11.4520 |
| gen tok/s (512) | 108.4990 ± 0.4910 | 94.2940 ± 0.3650 | 97.2820 ± 0.0800 | 89.4920 ± 0.2610 |
| kl divergence | 0.0838 ± 0.0008 | 0.1689 ± 0.0015 | 0.0244 ± 0.0004 | 0.0189 ± 0.0003 |
| perplexity | 4.6150 ± 0.0320 | 4.2490 ± 0.0280 | 4.6410 ± 0.0320 | 4.6440 ± 0.0320 |
| hellaswag | 0.5560 ± 0.0220 | 0.5780 ± 0.0220 | 0.5440 ± 0.0220 | 0.5370 ± 0.0110 |
| piqa | 0.7940 ± 0.0180 | 0.7920 ± 0.0180 | 0.7920 ± 0.0180 | 0.7980 ± 0.0180 |
| winogrande | 0.7260 ± 0.0200 | 0.7400 ± 0.0200 | 0.7120 ± 0.0200 | 0.7100 ± 0.0200 |
I've moved over to using speed + KL divergence as my primary optimization metrics. Hellaswag, PIQA, Winogrande, and perplexity are kept as sanity checks, though these require high sample sizes to get usable signal.
Tested on a Mac Studio M3 Ultra with:
mlx_lm.convert --hf-path Qwen/Qwen3.6-35B-A3B --mlx-path ./mlx && mlx_lm.kld --baseline-model ./mlx
mlx_lm.perplexity --sequence-length 512 --seed 123
mlx_lm.benchmark --prompt-tokens 1024 --generation-tokens 512 --num-trials 5
mlx_lm.evaluate --tasks hellaswag --seed 123 --num-shots 0 --limit 500
mlx_lm.evaluate --tasks piqa --seed 123 --num-shots 0 --limit 500
mlx_lm.evaluate --tasks winogrande --seed 123 --num-shots 0 --limit 500
mlx_lm.kld is still an open PR.
Methodology
Quantized with a mlx-lm fork, drawing inspiration from Unsloth/AesSedai/ubergarm style mixed-precision GGUFs. MLX quantization options differ than llama.cpp, but the principles are the same:
- Sensitive layers like MoE routing, attention, and output embeddings get higher precision
- More tolerant layers like MoE experts get lower precision