Is TildeOpen-30B-Instruct-LV or Qwen3-Coder-30B-A3B-Instruct smaller?

Both publish quantizations; compare the table for the exact sizes.

Which uses less memory at long context?

Qwen3-Coder-30B-A3B-Instruct — its KV cache at 32K context is 2.5x smaller, because of how its attention layers cache.

Model comparison

TildeOpen-30B-Instruct-LV vs Qwen3-Coder-30B-A3B-Instruct

These two publish different quantization sets; the table below has the exact sizes. At long context the gap widens: Qwen3-Coder-30B-A3B-Instruct's KV cache at 32K is 2.5× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	TildeOpen-30B-Instruct-LV	Qwen3-Coder-30B-A3B-Instruct
Parameters	30.7B	30.5B
Architecture	llama	qwen3moe
Layers	60	48
Native context	65,536	262,144
Mixture of experts	no	yes, 128 experts
Quantizations published	23	46
Smallest quantization	6.43 GiB	7.46 GiB
Q4_K_M	—	17.28 GiB
Licence	cc-by-4.0	apache-2.0

KV cache by context

the term that decides long-context viability

Context	TildeOpen-30B-Instruct-LV	Qwen3-Coder-30B-A3B-Instruct	Ratio
4,096	0.94 GiB	0.38 GiB	2.50×
8,192	1.88 GiB	0.75 GiB	2.50×
16,384	3.75 GiB	1.50 GiB	2.50×
32,768	7.50 GiB	3.00 GiB	2.50×
65,536	15.00 GiB	6.00 GiB	2.50×
131,072	30.00 GiB	12.00 GiB	2.50×