Model comparison

Teuken-7B-instruct-research-v0.4 vs Qwen3-4B

At Q4_K_M, Qwen3-4B is the smaller download — 2,497,280,256 bytes against 5,018,868,320. At long context the gap widens: Teuken-7B-instruct-research-v0.4's KV cache at 32K is 4.5× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

Teuken-7B-instruct-research-v0.4Qwen3-4B
Parameters7.5B4.0B
Architecturellamaqwen3
Layers3236
Native context4,09640,960
Mixture of expertsnono
Quantizations published4129
Smallest quantization2.48 GiB1.01 GiB
Q4_K_M4.67 GiB2.33 GiB
Licenceother

KV cache by context

the term that decides long-context viability
ContextTeuken-7B-instruct-research-v0.4Qwen3-4BRatio
4,0960.13 GiB0.56 GiB4.50×
8,1920.25 GiB1.13 GiB4.50×
16,3840.50 GiB2.25 GiB4.50×
32,7681.00 GiB4.50 GiB4.50×
65,5362.00 GiB9.00 GiB4.50×
131,0724.00 GiB18.00 GiB4.50×