Model comparison
SciPhi-Mistral-7B-32k vs Qwen3-30B-A3B-Thinking-2507
At Q4_K_M, SciPhi-Mistral-7B-32k is the smaller download — 4,368,438,912 bytes against 18,556,685,824.
From the file· summed bytes, KV per layer
Side by side
| SciPhi-Mistral-7B-32k | Qwen3-30B-A3B-Thinking-2507 | |
|---|---|---|
| Parameters | 7.2B | 30.5B |
| Architecture | llama | qwen3moe |
| Layers | 32 | 48 |
| Native context | 32,768 | 262,144 |
| Mixture of experts | no | yes, 128 experts |
| Quantizations published | 36 | 51 |
| Smallest quantization | 2.87 GiB | 7.05 GiB |
| Q4_K_M | 4.07 GiB | 17.28 GiB |
| Licence | llama2 | apache-2.0 |
KV cache by context
the term that decides long-context viability
| Context | SciPhi-Mistral-7B-32k | Qwen3-30B-A3B-Thinking-2507 | Ratio |
|---|---|---|---|
| 4,096 | — | 0.38 GiB | — |
| 8,192 | — | 0.75 GiB | — |
| 16,384 | — | 1.50 GiB | — |
| 32,768 | — | 3.00 GiB | — |
| 65,536 | — | 6.00 GiB | — |
| 131,072 | — | 12.00 GiB | — |