Model comparison
Qwen3.8-27B vs gemma-4-E4B-it-Claude-Opus-4.5-HERETIC-UNCENSORED-Thinking
At Q4_K_M, gemma-4-E4B-it-Claude-Opus-4.5-HERETIC-UNCENSORED-Thinking is the smaller download — 5,335,286,208 bytes against 16,810,714,336. At long context the gap widens: gemma-4-E4B-it-Claude-Opus-4.5-HERETIC-UNCENSORED-Thinking's KV cache at 32K is 4.0× smaller, which usually matters more than the difference in weights.
From the file· summed bytes, KV per layer
Side by side
| Qwen3.8-27B | gemma-4-E4B-it-Claude-Opus-4.5-HERETIC-UNCENSORED-Thinking | |
|---|---|---|
| Parameters | 27.8B | 8.0B |
| Architecture | qwen35 | gemma4 |
| Layers | 64 | 42 |
| Native context | 262,144 | 131,072 |
| Mixture of experts | no | no |
| Quantizations published | 22 | 27 |
| Smallest quantization | 8.39 GiB | 4.10 GiB |
| Q4_K_M | 15.66 GiB | 4.97 GiB |
| Licence | apache-2.0 | apache-2.0 |
KV cache by context
the term that decides long-context viability
| Context | Qwen3.8-27B | gemma-4-E4B-it-Claude-Opus-4.5-HERETIC-UNCENSORED-Thinking | Ratio |
|---|---|---|---|
| 4,096 | 0.25 GiB | 0.12 GiB | 2.03× |
| 8,192 | 0.50 GiB | 0.18 GiB | 2.81× |
| 16,384 | 1.00 GiB | 0.29 GiB | 3.48× |
| 32,768 | 2.00 GiB | 0.51 GiB | 3.95× |
| 65,536 | 4.00 GiB | 0.94 GiB | 4.24× |
| 131,072 | 8.00 GiB | 1.82 GiB | 4.40× |