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-CODER | gemma-4-E4B-it | |
|---|---|---|
| Parameters | 42.4B | 8.0B |
| Architecture | qwen3moe | gemma4 |
| Layers | 67 | 42 |
| Native context | 262,144 | 131,072 |
| Mixture of experts | yes, 128 experts | no |
| Quantizations published | 34 | 36 |
| Smallest quantization | 8.21 GiB | 3.30 GiB |
| Q4_K_M | 23.94 GiB | 4.64 GiB |
| Licence | apache-2.0 | apache-2.0 |
KV cache by context
the term that decides long-context viability
| Context | Qwen3-42B-A3B-2507-Thinking-Abliterated-uncensored-TOTAL-RECALL-v2-Medium-MASTER-CODER | gemma-4-E4B-it | Ratio |
|---|---|---|---|
| 4,096 | 0.52 GiB | 0.12 GiB | 4.25× |
| 8,192 | 1.05 GiB | 0.18 GiB | 5.89× |
| 16,384 | 2.09 GiB | 0.29 GiB | 7.29× |
| 32,768 | 4.19 GiB | 0.51 GiB | 8.28× |
| 65,536 | 8.38 GiB | 0.94 GiB | 8.88× |
| 131,072 | 16.75 GiB | 1.82 GiB | 9.21× |