Is Ternary-Bonsai-1.7B-unpacked or Qwen3-4B smaller?

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

Which uses less memory at long context?

Ternary-Bonsai-1.7B-unpacked — its KV cache at 32K context is 1.3x smaller, because of how its attention layers cache.

Model comparison

Ternary-Bonsai-1.7B-unpacked vs Qwen3-4B

These two publish different quantization sets; the table below has the exact sizes. At long context the gap widens: Ternary-Bonsai-1.7B-unpacked's KV cache at 32K is 1.3× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	Ternary-Bonsai-1.7B-unpacked	Qwen3-4B
Parameters	1.7B	4.0B
Architecture	qwen3	qwen3
Layers	28	36
Native context	32,768	40,960
Mixture of experts	no	no
Quantizations published	2	29
Smallest quantization	0.43 GiB	1.01 GiB
Q4_K_M	—	2.33 GiB
Licence	apache-2.0	—

KV cache by context

the term that decides long-context viability

Context	Ternary-Bonsai-1.7B-unpacked	Qwen3-4B	Ratio
4,096	0.44 GiB	0.56 GiB	1.29×
8,192	0.88 GiB	1.13 GiB	1.29×
16,384	1.75 GiB	2.25 GiB	1.29×
32,768	3.50 GiB	4.50 GiB	1.29×
65,536	7.00 GiB	9.00 GiB	1.29×
131,072	14.00 GiB	18.00 GiB	1.29×