Model comparison
Qwen3.8-27B vs OpenAI-gpt-oss-20B-Claude-4.5-Opus-Heretic-Uncensored
These two publish different quantization sets; the table below has the exact sizes. At long context the gap widens: OpenAI-gpt-oss-20B-Claude-4.5-Opus-Heretic-Uncensored's KV cache at 32K is 2.6× smaller, which usually matters more than the difference in weights.
From the file· summed bytes, KV per layer
Side by side
| Qwen3.8-27B | OpenAI-gpt-oss-20B-Claude-4.5-Opus-Heretic-Uncensored | |
|---|---|---|
| Parameters | 27.8B | 20.9B |
| Architecture | qwen35 | gpt-oss |
| Layers | 64 | 24 |
| Native context | 262,144 | 131,072 |
| Mixture of experts | no | yes, 32 experts |
| Quantizations published | 22 | 47 |
| Smallest quantization | 8.39 GiB | 11.19 GiB |
| Q4_K_M | 15.66 GiB | — |
| Licence | apache-2.0 | apache-2.0 |
KV cache by context
the term that decides long-context viability
| Context | Qwen3.8-27B | OpenAI-gpt-oss-20B-Claude-4.5-Opus-Heretic-Uncensored | Ratio |
|---|---|---|---|
| 4,096 | 0.25 GiB | 0.11 GiB | 2.25× |
| 8,192 | 0.50 GiB | 0.21 GiB | 2.44× |
| 16,384 | 1.00 GiB | 0.39 GiB | 2.55× |
| 32,768 | 2.00 GiB | 0.77 GiB | 2.61× |
| 65,536 | 4.00 GiB | 1.52 GiB | 2.64× |
| 131,072 | 8.00 GiB | 3.02 GiB | 2.65× |