Model comparison
nomic-embed-code vs Qwen3-Embedding-8B
At Q4_K_M, nomic-embed-code is the smaller download — 4,376,511,808 bytes against 4,676,804,928. At long context the gap widens: nomic-embed-code's KV cache at 32K is 2.6× smaller, which usually matters more than the difference in weights.
From the file· summed bytes, KV per layer
Side by side
| nomic-embed-code | Qwen3-Embedding-8B | |
|---|---|---|
| Parameters | 7.1B | 7.6B |
| Architecture | qwen2 | qwen3 |
| Layers | 28 | 36 |
| Native context | 32,768 | 40,960 |
| Mixture of experts | no | no |
| Quantizations published | 42 | 17 |
| Smallest quantization | 2.37 GiB | 2.87 GiB |
| Q4_K_M | 4.08 GiB | 4.36 GiB |
| Licence | apache-2.0 | apache-2.0 |
KV cache by context
the term that decides long-context viability
| Context | nomic-embed-code | Qwen3-Embedding-8B | Ratio |
|---|---|---|---|
| 4,096 | 0.22 GiB | 0.56 GiB | 2.57× |
| 8,192 | 0.44 GiB | 1.13 GiB | 2.57× |
| 16,384 | 0.88 GiB | 2.25 GiB | 2.57× |
| 32,768 | 1.75 GiB | 4.50 GiB | 2.57× |
| 65,536 | 3.50 GiB | 9.00 GiB | 2.57× |
| 131,072 | 7.00 GiB | 18.00 GiB | 2.57× |