Model comparison
smollm-360M-instruct-add-basics vs MiniCPM5-1B-Claude-Opus-Fable5-Thinking
These two publish different quantization sets; the table below has the exact sizes. At long context the gap widens: MiniCPM5-1B-Claude-Opus-Fable5-Thinking's KV cache at 32K is 1.7× smaller, which usually matters more than the difference in weights.
From the file· summed bytes, KV per layer
Side by side
| smollm-360M-instruct-add-basics | MiniCPM5-1B-Claude-Opus-Fable5-Thinking | |
|---|---|---|
| Parameters | 362M | 1.1B |
| Architecture | llama | llama |
| Layers | 32 | 24 |
| Native context | 2,048 | 131,072 |
| Mixture of experts | no | no |
| Quantizations published | 8 | 15 |
| Smallest quantization | 0.19 GiB | 0.43 GiB |
| Q4_K_M | — | 0.64 GiB |
| Licence | — | apache-2.0 |
KV cache by context
the term that decides long-context viability
| Context | smollm-360M-instruct-add-basics | MiniCPM5-1B-Claude-Opus-Fable5-Thinking | Ratio |
|---|---|---|---|
| 4,096 | 0.16 GiB | 0.09 GiB | 1.67× |
| 8,192 | 0.31 GiB | 0.19 GiB | 1.67× |
| 16,384 | 0.63 GiB | 0.38 GiB | 1.67× |
| 32,768 | 1.25 GiB | 0.75 GiB | 1.67× |
| 65,536 | 2.50 GiB | 1.50 GiB | 1.67× |
| 131,072 | 5.00 GiB | 3.00 GiB | 1.67× |