A 30%-expert-pruned and router-healed MLX 8-bit derivative of mlx-community/Qwen3.6-35B-A3B-8bit, using a per-layer adaptive budget (variable expert count per layer).

30% removed overall, with per-layer counts varying (143–245, mean 179) — more experts kept in language-structure-heavy early layers, fewer in language-specialized late layers (allocation by English routing warmth, floor 16). Routers then recalibrated with Router-KD (rank-64 LoRA on mlp.gate, ~5.7M params, wikitext calibration), fused.


Routed experts	143–245/layer (mean 179, −30% total)
Active	top-8 + 1 shared
Healing	Router-KD (router-only)
Format	MLX, 8-bit

⚠️ Loading — variable expert counts require `strict=False`

Standard mlx_lm.load is strict and will fail with a shape mismatch. Load with strict=False:

python

from pathlib import Path
from huggingface_hub import snapshot_download
from mlx_lm.utils import load_model, load_tokenizer

path = Path(snapshot_download("neopolita/Qwen3.6-35B-A3B-8bit-Prune-30-Adaptive"))
model, _ = load_model(path, strict=False)   # adopts the per-layer shapes
tok = load_tokenizer(path)

The MoE forward routes on each layer's gate width + top-k (never a global num_experts), so the variable model runs correctly once loaded with strict=False.

Benchmarks (healed model vs unpruned base; 100–200 samples)

metric	base	this model
wikitext PPL	7.98	8.63
winogrande	0.70	0.725
hellaswag (acc_norm)	0.555	0.585
piqa (acc_norm)	0.84	0.81
gsm8k (strict)	0.99	0.97
ifeval (prompt-strict)	0.86	0.82
ifeval (inst-loose)	0.933	0.896

At 30% the prune is near-free on most downstream tasks. (On the uniform 30% variant, Router-KD also fully recovers instruction-following / IFEval; on this adaptive variant the heal is roughly task-neutral and mainly recovers perplexity.)

Notes

Research artifact. Selection by per-layer English routing frequency (not REAP); small-sample benchmarks (100–200). License/usage inherit from the base model.

neopolita/Qwen3.6-35B-A3B-8bit-Prune-30-Adaptive

Qwen3.6-35B-A3B-8bit-Prune-30-Adaptive

⚠️ Loading — variable expert counts require strict=False

Benchmarks (healed model vs unpruned base; 100–200 samples)

Notes

neopolita/
Qwen3.6-35B-A3B-8bit-Prune-30-Adaptive

⚠️ Loading — variable expert counts require `strict=False`