Model comparison
OpenCoder-1.5B-Instruct vs Qwen3-VL-8B-Instruct-abliterated-v1
At Q4_K_M, OpenCoder-1.5B-Instruct is the smaller download — 1,417,775,200 bytes against 5,027,785,792.
From the file· summed bytes, KV per layer
Side by side
| OpenCoder-1.5B-Instruct | Qwen3-VL-8B-Instruct-abliterated-v1 | |
|---|---|---|
| Parameters | 1.9B | 8.8B |
| Architecture | llama | qwen3vl |
| Layers | 24 | — |
| Native context | 4,096 | — |
| Mixture of experts | no | no |
| Quantizations published | 4 | 48 |
| Smallest quantization | 1.18 GiB | 1.97 GiB |
| Q4_K_M | 1.32 GiB | 4.68 GiB |
| Licence | other | apache-2.0 |
KV cache by context
the term that decides long-context viability
| Context | OpenCoder-1.5B-Instruct | Qwen3-VL-8B-Instruct-abliterated-v1 | Ratio |
|---|---|---|---|
| 4,096 | 0.82 GiB | — | — |
| 8,192 | 1.64 GiB | — | — |
| 16,384 | 3.28 GiB | — | — |
| 32,768 | 6.56 GiB | — | — |
| 65,536 | 13.13 GiB | — | — |
| 131,072 | 26.25 GiB | — | — |