Model comparison
Qwen3.5-9B vs Qwen3.5-9B-Claude-4.6-OS-Auto-Variable-HERETIC-UNCENSORED-THINKING
These two publish different quantization sets; the table below has the exact sizes.
From the file· summed bytes, KV per layer
Side by side
| Qwen3.5-9B | Qwen3.5-9B-Claude-4.6-OS-Auto-Variable-HERETIC-UNCENSORED-THINKING | |
|---|---|---|
| Parameters | 9.7B | 9.4B |
| Architecture | qwen35 | qwen35 |
| Layers | 32 | 32 |
| Native context | 262,144 | 262,144 |
| Mixture of experts | no | no |
| Quantizations published | 34 | 26 |
| Smallest quantization | 2.97 GiB | 2.28 GiB |
| Q4_K_M | 5.24 GiB | — |
| Licence | apache-2.0 | apache-2.0 |
KV cache by context
the term that decides long-context viability
| Context | Qwen3.5-9B | Qwen3.5-9B-Claude-4.6-OS-Auto-Variable-HERETIC-UNCENSORED-THINKING | Ratio |
|---|---|---|---|
| 4,096 | 0.13 GiB | 0.13 GiB | 1.00× |
| 8,192 | 0.25 GiB | 0.25 GiB | 1.00× |
| 16,384 | 0.50 GiB | 0.50 GiB | 1.00× |
| 32,768 | 1.00 GiB | 1.00 GiB | 1.00× |
| 65,536 | 2.00 GiB | 2.00 GiB | 1.00× |
| 131,072 | 4.00 GiB | 4.00 GiB | 1.00× |