Model comparison
Bonsai-8B-unpacked vs Qwen3-8B
At Q4_K_M, Qwen3-8B is the smaller download — 5,027,783,488 bytes against 5,198,494,208.
From the file· summed bytes, KV per layer
Side by side
| Bonsai-8B-unpacked | Qwen3-8B | |
|---|---|---|
| Parameters | 8.2B | 8.2B |
| Architecture | qwen3 | qwen3 |
| Layers | 36 | 36 |
| Native context | 65,536 | 40,960 |
| Mixture of experts | no | no |
| Quantizations published | 23 | 51 |
| Smallest quantization | 3.13 GiB | 2.12 GiB |
| Q4_K_M | 4.84 GiB | 4.68 GiB |
| Licence | apache-2.0 | apache-2.0 |
KV cache by context
the term that decides long-context viability
| Context | Bonsai-8B-unpacked | Qwen3-8B | Ratio |
|---|---|---|---|
| 4,096 | 0.56 GiB | 0.56 GiB | 1.00× |
| 8,192 | 1.13 GiB | 1.13 GiB | 1.00× |
| 16,384 | 2.25 GiB | 2.25 GiB | 1.00× |
| 32,768 | 4.50 GiB | 4.50 GiB | 1.00× |
| 65,536 | 9.00 GiB | 9.00 GiB | 1.00× |
| 131,072 | 18.00 GiB | 18.00 GiB | 1.00× |