Model comparison
Qwen3.6-9B-Heretic-Uncensored-Thinking-Sweet-Madness vs gemma-4-12B-it
At Q4_K_M, Qwen3.6-9B-Heretic-Uncensored-Thinking-Sweet-Madness is the smaller download — 5,463,652,192 bytes against 7,121,861,440. At long context the gap widens: Qwen3.6-9B-Heretic-Uncensored-Thinking-Sweet-Madness's KV cache at 32K is 4.9× smaller, which usually matters more than the difference in weights.
From the file· summed bytes, KV per layer
Side by side
| Qwen3.6-9B-Heretic-Uncensored-Thinking-Sweet-Madness | gemma-4-12B-it | |
|---|---|---|
| Parameters | 9.1B | 12.0B |
| Architecture | qwen35 | gemma4 |
| Layers | 16 | 48 |
| Native context | 262,144 | 262,144 |
| Mixture of experts | no | no |
| Quantizations published | 2 | 59 |
| Smallest quantization | 4.88 GiB | 3.92 GiB |
| Q4_K_M | 5.09 GiB | 6.63 GiB |
| Licence | apache-2.0 | apache-2.0 |
KV cache by context
the term that decides long-context viability
| Context | Qwen3.6-9B-Heretic-Uncensored-Thinking-Sweet-Madness | gemma-4-12B-it | Ratio |
|---|---|---|---|
| 4,096 | 0.06 GiB | 0.72 GiB | 11.49× |
| 8,192 | 0.13 GiB | 0.97 GiB | 7.75× |
| 16,384 | 0.25 GiB | 1.47 GiB | 5.87× |
| 32,768 | 0.50 GiB | 2.47 GiB | 4.94× |
| 65,536 | 1.00 GiB | 4.47 GiB | 4.47× |
| 131,072 | 2.00 GiB | 8.47 GiB | 4.23× |