Model comparison
reasoning-summarizer-800m-pre vs Qwen3-4B
At Q4_K_M, reasoning-summarizer-800m-pre is the smaller download — 529,289,792 bytes against 2,497,280,256. At long context the gap widens: reasoning-summarizer-800m-pre's KV cache at 32K is 12.0× smaller, which usually matters more than the difference in weights.
From the file· summed bytes, KV per layer
Side by side
| reasoning-summarizer-800m-pre | Qwen3-4B | |
|---|---|---|
| Parameters | 752M | 4.0B |
| Architecture | qwen35 | qwen3 |
| Layers | 24 | 36 |
| Native context | 262,144 | 40,960 |
| Mixture of experts | no | no |
| Quantizations published | 6 | 29 |
| Smallest quantization | 0.47 GiB | 1.01 GiB |
| Q4_K_M | 0.49 GiB | 2.33 GiB |
| Licence | apache-2.0 | — |
KV cache by context
the term that decides long-context viability
| Context | reasoning-summarizer-800m-pre | Qwen3-4B | Ratio |
|---|---|---|---|
| 4,096 | 0.05 GiB | 0.56 GiB | 11.99× |
| 8,192 | 0.09 GiB | 1.13 GiB | 12.00× |
| 16,384 | 0.19 GiB | 2.25 GiB | 12.00× |
| 32,768 | 0.38 GiB | 4.50 GiB | 12.00× |
| 65,536 | 0.75 GiB | 9.00 GiB | 12.00× |
| 131,072 | 1.50 GiB | 18.00 GiB | 12.00× |