Model comparison

Qwen3-42B-A3B-2507-Thinking-Abliterated-uncensored-TOTAL-RECALL-v2-Medium-MASTER-CODER vs gemma-4-E4B-it

At Q4_K_M, gemma-4-E4B-it is the smaller download — 4,977,171,584 bytes against 25,703,283,040. At long context the gap widens: gemma-4-E4B-it's KV cache at 32K is 8.3× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

Qwen3-42B-A3B-2507-Thinking-Abliterated-uncensored-TOTAL-RECALL-v2-Medium-MASTER-CODERgemma-4-E4B-it
Parameters42.4B8.0B
Architectureqwen3moegemma4
Layers6742
Native context262,144131,072
Mixture of expertsyes, 128 expertsno
Quantizations published3436
Smallest quantization8.21 GiB3.30 GiB
Q4_K_M23.94 GiB4.64 GiB
Licenceapache-2.0apache-2.0

KV cache by context

the term that decides long-context viability
ContextQwen3-42B-A3B-2507-Thinking-Abliterated-uncensored-TOTAL-RECALL-v2-Medium-MASTER-CODERgemma-4-E4B-itRatio
4,0960.52 GiB0.12 GiB4.25×
8,1921.05 GiB0.18 GiB5.89×
16,3842.09 GiB0.29 GiB7.29×
32,7684.19 GiB0.51 GiB8.28×
65,5368.38 GiB0.94 GiB8.88×
131,07216.75 GiB1.82 GiB9.21×