Model comparison
LocalAI-functioncall-qwen2.5-7b-v0.5 vs Qwen3-Coder-30B-A3B-Instruct
At Q4_K_M, LocalAI-functioncall-qwen2.5-7b-v0.5 is the smaller download — 4,683,074,048 bytes against 18,556,689,568. At long context the gap widens: LocalAI-functioncall-qwen2.5-7b-v0.5'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
| LocalAI-functioncall-qwen2.5-7b-v0.5 | Qwen3-Coder-30B-A3B-Instruct | |
|---|---|---|
| Parameters | 7.6B | 30.5B |
| Architecture | qwen2 | qwen3moe |
| Layers | 28 | 48 |
| Native context | 32,768 | 262,144 |
| Mixture of experts | no | yes, 128 experts |
| Quantizations published | 1 | 46 |
| Smallest quantization | 4.36 GiB | 7.46 GiB |
| Q4_K_M | 4.36 GiB | 17.28 GiB |
| Licence | apache-2.0 | apache-2.0 |
KV cache by context
the term that decides long-context viability
| Context | LocalAI-functioncall-qwen2.5-7b-v0.5 | Qwen3-Coder-30B-A3B-Instruct | Ratio |
|---|---|---|---|
| 4,096 | 0.22 GiB | 0.38 GiB | 1.71× |
| 8,192 | 0.44 GiB | 0.75 GiB | 1.71× |
| 16,384 | 0.88 GiB | 1.50 GiB | 1.71× |
| 32,768 | 1.75 GiB | 3.00 GiB | 1.71× |
| 65,536 | 3.50 GiB | 6.00 GiB | 1.71× |
| 131,072 | 7.00 GiB | 12.00 GiB | 1.71× |