Model comparison
PINQWEN-3.5-9B-1M-BF16 vs Qwen3-Coder-30B-A3B-Instruct
At Q4_K_M, PINQWEN-3.5-9B-1M-BF16 is the smaller download — 5,780,091,328 bytes against 18,556,689,568. At long context the gap widens: PINQWEN-3.5-9B-1M-BF16's KV cache at 32K is 3.0× smaller, which usually matters more than the difference in weights.
From the file· summed bytes, KV per layer
Side by side
| PINQWEN-3.5-9B-1M-BF16 | Qwen3-Coder-30B-A3B-Instruct | |
|---|---|---|
| Parameters | 9.7B | 30.5B |
| Architecture | qwen35 | qwen3moe |
| Layers | 32 | 48 |
| Native context | 1,048,576 | 262,144 |
| Mixture of experts | no | yes, 128 experts |
| Quantizations published | 27 | 46 |
| Smallest quantization | 3.65 GiB | 7.46 GiB |
| Q4_K_M | 5.38 GiB | 17.28 GiB |
| Licence | apache-2.0 | apache-2.0 |
KV cache by context
the term that decides long-context viability
| Context | PINQWEN-3.5-9B-1M-BF16 | Qwen3-Coder-30B-A3B-Instruct | Ratio |
|---|---|---|---|
| 4,096 | 0.13 GiB | 0.38 GiB | 3.00× |
| 8,192 | 0.25 GiB | 0.75 GiB | 3.00× |
| 16,384 | 0.50 GiB | 1.50 GiB | 3.00× |
| 32,768 | 1.00 GiB | 3.00 GiB | 3.00× |
| 65,536 | 2.00 GiB | 6.00 GiB | 3.00× |
| 131,072 | 4.00 GiB | 12.00 GiB | 3.00× |