Model comparison
GLM-4.7-Flash-REAP-23B-A3B vs Qwen3-Coder-30B-A3B-Instruct
At Q4_K_M, GLM-4.7-Flash-REAP-23B-A3B is the smaller download — 14,113,838,816 bytes against 18,556,689,568. At long context the gap widens: GLM-4.7-Flash-REAP-23B-A3B's KV cache at 32K is 1.8× smaller, which usually matters more than the difference in weights.
From the file· summed bytes, KV per layer
Side by side
| GLM-4.7-Flash-REAP-23B-A3B | Qwen3-Coder-30B-A3B-Instruct | |
|---|---|---|
| Parameters | 23.0B | 30.5B |
| Architecture | deepseek2 | qwen3moe |
| Layers | 47 | 48 |
| Native context | 202,752 | 262,144 |
| Mixture of experts | yes, 48 experts | yes, 128 experts |
| Quantizations published | 21 | 46 |
| Smallest quantization | 6.09 GiB | 7.46 GiB |
| Q4_K_M | 13.14 GiB | 17.28 GiB |
| Licence | mit | apache-2.0 |
KV cache by context
the term that decides long-context viability
| Context | GLM-4.7-Flash-REAP-23B-A3B | Qwen3-Coder-30B-A3B-Instruct | Ratio |
|---|---|---|---|
| 4,096 | 0.21 GiB | 0.38 GiB | 1.82× |
| 8,192 | 0.41 GiB | 0.75 GiB | 1.82× |
| 16,384 | 0.83 GiB | 1.50 GiB | 1.82× |
| 32,768 | 1.65 GiB | 3.00 GiB | 1.82× |
| 65,536 | 3.30 GiB | 6.00 GiB | 1.82× |
| 131,072 | 6.61 GiB | 12.00 GiB | 1.82× |