Model comparison
Qwen3-Coder-30B-A3B-Instruct vs Gemma-3-27B-MeditronFO
At Q4_K_M, Gemma-3-27B-MeditronFO is the smaller download — 17,339,606,784 bytes against 18,556,689,568.
From the file· summed bytes, KV per layer
Side by side
| Qwen3-Coder-30B-A3B-Instruct | Gemma-3-27B-MeditronFO | |
|---|---|---|
| Parameters | 30.5B | 28.8B |
| Architecture | qwen3moe | gemma3 |
| Layers | 48 | 62 |
| Native context | 262,144 | — |
| Mixture of experts | yes, 128 experts | no |
| Quantizations published | 46 | 34 |
| Smallest quantization | 7.46 GiB | 6.26 GiB |
| Q4_K_M | 17.28 GiB | 16.15 GiB |
| Licence | apache-2.0 | gemma |
KV cache by context
the term that decides long-context viability
| Context | Qwen3-Coder-30B-A3B-Instruct | Gemma-3-27B-MeditronFO | Ratio |
|---|---|---|---|
| 4,096 | 0.38 GiB | 0.92 GiB | 2.46× |
| 8,192 | 0.75 GiB | 1.23 GiB | 1.65× |
| 16,384 | 1.50 GiB | 1.86 GiB | 1.24× |
| 32,768 | 3.00 GiB | 3.11 GiB | 1.04× |
| 65,536 | 6.00 GiB | 5.61 GiB | 1.07× |
| 131,072 | 12.00 GiB | 10.61 GiB | 1.13× |