OuteTTS-0.3-1B-GGUF
Original Model
Run with LlamaEdge
- LlamaEdge version: coming soon
Quantized GGUF Models
Name | Quant method | Bits | Size | Use case |
---|---|---|---|---|
OuteTTS-0.3-1B-Q2_K.gguf | Q2_K | 2 | 491 MB | smallest, significant quality loss - not recommended for most purposes |
OuteTTS-0.3-1B-Q3_K_L.gguf | Q3_K_L | 3 | 663 MB | small, substantial quality loss |
OuteTTS-0.3-1B-Q3_K_M.gguf | Q3_K_M | 3 | 616 MB | very small, high quality loss |
OuteTTS-0.3-1B-Q3_K_S.gguf | Q3_K_S | 3 | 560 MB | very small, high quality loss |
OuteTTS-0.3-1B-Q4_0.gguf | Q4_0 | 4 | 702 MB | legacy; small, very high quality loss - prefer using Q3_K_M |
OuteTTS-0.3-1B-Q4_K_M.gguf | Q4_K_M | 4 | 745 MB | medium, balanced quality - recommended |
OuteTTS-0.3-1B-Q4_K_S.gguf | Q4_K_S | 4 | 709 MB | small, greater quality loss |
OuteTTS-0.3-1B-Q5_0.gguf | Q5_0 | 5 | 836 MB | legacy; medium, balanced quality - prefer using Q4_K_M |
OuteTTS-0.3-1B-Q5_K_M.gguf | Q5_K_M | 5 | 859 MB | large, very low quality loss - recommended |
OuteTTS-0.3-1B-Q5_K_S.gguf | Q5_K_S | 5 | 836 MB | large, low quality loss - recommended |
OuteTTS-0.3-1B-Q6_K.gguf | Q6_K | 6 | 979 MB | very large, extremely low quality loss |
OuteTTS-0.3-1B-Q8_0.gguf | Q8_0 | 8 | 1.27 GB | very large, extremely low quality loss - not recommended |
OuteTTS-0.3-1B-f16.gguf | f16 | 16 | 2.38 GB | |
wavtokenizer-large-75-ggml-f16.gguf | f16 | 16 | 1.00 GB |
Quantized with llama.cpp b4497
- Downloads last month
- 91
Model tree for second-state/OuteTTS-0.3-1B-GGUF
Base model
OuteAI/OuteTTS-0.3-1B