Qwen/Qwen3-30B-A3B

huggingface-mic/Qwen3-30B-A3B-mic@02a209fca462 ← Qwen/Qwen3-30B-A3B@ad44e777bcd1 · Qwen3MoeForCausalLM · random weights · built before the shrink rule (no recorded recipe)

Original30.5Bparameters

Fixture19.5Mparameters

Layer stacks1compared

Findings0to review

✓ Same architecture, smaller

Every module class, layer kind and checked property of the original is in the fixture.

One square per layer, colored by kind: the layer's module classes and type attributes. Hover a square for its index and kind.

Original · 48

Fixture · 2

Kind	Original	Fixture
DecoderLayer	48	2	✓ kept

Share of each model's parameters per component. Vocabulary and patch sizes are kept, so embeddings usually take a larger share of the fixture.

Original

Fixture

Component	Original	Share	Fixture	Share
model.layers	29.9B	98.0%	74.6K	0.4%
model.embed_tokens	311.2M	1.0%	9.7M	49.8%
lm_head	311.2M	1.0%	9.7M	49.8%
model.norm	2.0K	0.0%	64	0.0%

Config	Property	Original	Fixture
model	attention style	GQA (32 heads, 4 KV)	GQA (4 heads, 2 KV)	✓ kept
model	MoE routing	top-8 of 128 experts	top-2 of 4 experts	✓ kept
model	RoPE type	default	default	✓ kept
model	model_type	qwen3_moe	qwen3_moe	✓ kept
model	vocab_size	151936	151936	✓ kept
model	tie_word_embeddings	False	False	✓ kept
model	hidden_act	silu	silu	✓ kept
model	max_position_embeddings	40960	40960	✓ kept

Instances of each class in the built model (prefix Qwen3Moe omitted).

9 fields changed, 30 unchanged.