Model comparison
Garnet-OCR-3B-0422 vs Llama-3.1-8B-Instruct
At Q4_K_M, Garnet-OCR-3B-0422 is the smaller download — 2,104,202,944 bytes against 4,920,739,168. At long context the gap widens: Garnet-OCR-3B-0422's KV cache at 32K is 3.6× smaller, which usually matters more than the difference in weights.
From the file· summed bytes, KV per layer
Side by side
| Garnet-OCR-3B-0422 | Llama-3.1-8B-Instruct | |
|---|---|---|
| Parameters | 4.1B | 8.0B |
| Architecture | qwen2vl | llama |
| Layers | 36 | 32 |
| Native context | 128,000 | 131,072 |
| Mixture of experts | no | no |
| Quantizations published | 36 | 45 |
| Smallest quantization | 0.83 GiB | 2.02 GiB |
| Q4_K_M | 1.96 GiB | 4.58 GiB |
| Licence | apache-2.0 | llama3.1 |
KV cache by context
the term that decides long-context viability
| Context | Garnet-OCR-3B-0422 | Llama-3.1-8B-Instruct | Ratio |
|---|---|---|---|
| 4,096 | 0.14 GiB | 0.50 GiB | 3.56× |
| 8,192 | 0.28 GiB | 1.00 GiB | 3.56× |
| 16,384 | 0.56 GiB | 2.00 GiB | 3.56× |
| 32,768 | 1.13 GiB | 4.00 GiB | 3.56× |
| 65,536 | 2.25 GiB | 8.00 GiB | 3.56× |
| 131,072 | 4.50 GiB | 16.00 GiB | 3.56× |