Model comparison
Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-MTP vs Ornith-Agents-A1-3.6-35B-A3B-dare_ties
At Q4_K_M, Ornith-Agents-A1-3.6-35B-A3B-dare_ties is the smaller download — 21,166,758,208 bytes against 36,545,830,912. At long context the gap widens: Ornith-Agents-A1-3.6-35B-A3B-dare_ties's KV cache at 32K is 3.2× smaller, which usually matters more than the difference in weights.
From the file· summed bytes, KV per layer
Side by side
| Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-MTP | Ornith-Agents-A1-3.6-35B-A3B-dare_ties | |
|---|---|---|
| Parameters | 27.8B | 34.7B |
| Architecture | qwen35 | qwen35moe |
| Layers | 64 | 40 |
| Native context | 262,144 | 262,144 |
| Mixture of experts | no | yes, 256 experts |
| Quantizations published | 34 | 13 |
| Smallest quantization | 10.12 GiB | 15.61 GiB |
| Q4_K_M | 34.04 GiB | 19.71 GiB |
| Licence | apache-2.0 | apache-2.0 |
KV cache by context
the term that decides long-context viability
| Context | Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-MTP | Ornith-Agents-A1-3.6-35B-A3B-dare_ties | Ratio |
|---|---|---|---|
| 4,096 | 0.25 GiB | 0.08 GiB | 3.20× |
| 8,192 | 0.50 GiB | 0.16 GiB | 3.20× |
| 16,384 | 1.00 GiB | 0.31 GiB | 3.20× |
| 32,768 | 2.00 GiB | 0.63 GiB | 3.20× |
| 65,536 | 4.00 GiB | 1.25 GiB | 3.20× |
| 131,072 | 8.00 GiB | 2.50 GiB | 3.20× |