Model comparison
TinyLlama-1.1B-Chat-v1.0 vs Qwen3-1.7B
At Q4_K_M, TinyLlama-1.1B-Chat-v1.0 is the smaller download — 667,814,880 bytes against 1,107,409,472. At long context the gap widens: TinyLlama-1.1B-Chat-v1.0's KV cache at 32K is 5.1× smaller, which usually matters more than the difference in weights.
From the file· summed bytes, KV per layer
Side by side
| TinyLlama-1.1B-Chat-v1.0 | Qwen3-1.7B | |
|---|---|---|
| Parameters | 1.1B | 2.0B |
| Architecture | llama | qwen3 |
| Layers | 22 | 28 |
| Native context | 2,048 | 40,960 |
| Mixture of experts | no | no |
| Quantizations published | 26 | 48 |
| Smallest quantization | 0.45 GiB | 0.50 GiB |
| Q4_K_M | 0.62 GiB | 1.03 GiB |
| Licence | apache-2.0 | — |
KV cache by context
the term that decides long-context viability
| Context | TinyLlama-1.1B-Chat-v1.0 | Qwen3-1.7B | Ratio |
|---|---|---|---|
| 4,096 | 0.09 GiB | 0.44 GiB | 5.09× |
| 8,192 | 0.17 GiB | 0.88 GiB | 5.09× |
| 16,384 | 0.34 GiB | 1.75 GiB | 5.09× |
| 32,768 | 0.69 GiB | 3.50 GiB | 5.09× |
| 65,536 | 1.38 GiB | 7.00 GiB | 5.09× |
| 131,072 | 2.75 GiB | 14.00 GiB | 5.09× |