Model comparison
MiniCPM5-1B-Claude-Opus-Fable5-V2-Thinking vs Qwen3-1.7B
At Q4_K_M, MiniCPM5-1B-Claude-Opus-Fable5-V2-Thinking is the smaller download — 688,066,528 bytes against 1,107,409,472. At long context the gap widens: MiniCPM5-1B-Claude-Opus-Fable5-V2-Thinking's KV cache at 32K is 4.7× smaller, which usually matters more than the difference in weights.
From the file· summed bytes, KV per layer
Side by side
| MiniCPM5-1B-Claude-Opus-Fable5-V2-Thinking | Qwen3-1.7B | |
|---|---|---|
| Parameters | 1.1B | 2.0B |
| Architecture | llama | qwen3 |
| Layers | 24 | 28 |
| Native context | 131,072 | 40,960 |
| Mixture of experts | no | no |
| Quantizations published | 10 | 48 |
| Smallest quantization | 0.64 GiB | 0.50 GiB |
| Q4_K_M | 0.64 GiB | 1.03 GiB |
| Licence | apache-2.0 | — |
KV cache by context
the term that decides long-context viability
| Context | MiniCPM5-1B-Claude-Opus-Fable5-V2-Thinking | Qwen3-1.7B | Ratio |
|---|---|---|---|
| 4,096 | 0.09 GiB | 0.44 GiB | 4.67× |
| 8,192 | 0.19 GiB | 0.88 GiB | 4.67× |
| 16,384 | 0.38 GiB | 1.75 GiB | 4.67× |
| 32,768 | 0.75 GiB | 3.50 GiB | 4.67× |
| 65,536 | 1.50 GiB | 7.00 GiB | 4.67× |
| 131,072 | 3.00 GiB | 14.00 GiB | 4.67× |