Model comparison
Qwen3.8-27B vs DeepSeek-V2-Lite-Chat-Uncensored-Unbiased-Reasoner
At Q4_K_M, DeepSeek-V2-Lite-Chat-Uncensored-Unbiased-Reasoner is the smaller download — 10,361,112,672 bytes against 16,810,714,336. At long context the gap widens: DeepSeek-V2-Lite-Chat-Uncensored-Unbiased-Reasoner's KV cache at 32K is 2.1× smaller, which usually matters more than the difference in weights.
From the file· summed bytes, KV per layer
Side by side
| Qwen3.8-27B | DeepSeek-V2-Lite-Chat-Uncensored-Unbiased-Reasoner | |
|---|---|---|
| Parameters | 27.8B | 15.7B |
| Architecture | qwen35 | deepseek2 |
| Layers | 64 | 27 |
| Native context | 262,144 | 4,096 |
| Mixture of experts | no | yes, 64 experts |
| Quantizations published | 22 | 12 |
| Smallest quantization | 8.39 GiB | 5.99 GiB |
| Q4_K_M | 15.66 GiB | 9.65 GiB |
| Licence | apache-2.0 | llama3.3 |
KV cache by context
the term that decides long-context viability
| Context | Qwen3.8-27B | DeepSeek-V2-Lite-Chat-Uncensored-Unbiased-Reasoner | Ratio |
|---|---|---|---|
| 4,096 | 0.25 GiB | 0.12 GiB | 2.11× |
| 8,192 | 0.50 GiB | 0.24 GiB | 2.11× |
| 16,384 | 1.00 GiB | 0.47 GiB | 2.11× |
| 32,768 | 2.00 GiB | 0.95 GiB | 2.11× |
| 65,536 | 4.00 GiB | 1.90 GiB | 2.11× |
| 131,072 | 8.00 GiB | 3.80 GiB | 2.11× |