Model comparison
orpheus-3b-0.1-ft vs OmniVoice
At Q4_K_M, OmniVoice is the smaller download — 659,959,328 bytes against 2,092,567,712.
From the file· summed bytes, KV per layer
Side by side
| orpheus-3b-0.1-ft | OmniVoice | |
|---|---|---|
| Parameters | 3.8B | 613M |
| Architecture | llama | omnivoice-lm |
| Layers | 28 | — |
| Native context | 131,072 | — |
| Mixture of experts | no | no |
| Quantizations published | 22 | 7 |
| Smallest quantization | 0.91 GiB | 0.56 GiB |
| Q4_K_M | 1.95 GiB | 0.61 GiB |
| Licence | apache-2.0 | apache-2.0 |
KV cache by context
the term that decides long-context viability
| Context | orpheus-3b-0.1-ft | OmniVoice | Ratio |
|---|---|---|---|
| 4,096 | 0.44 GiB | — | — |
| 8,192 | 0.88 GiB | — | — |
| 16,384 | 1.75 GiB | — | — |
| 32,768 | 3.50 GiB | — | — |
| 65,536 | 7.00 GiB | — | — |
| 131,072 | 14.00 GiB | — | — |