Downloads · 30 days
526
12% of all-time downloads
second-state/SeaLLMs-Audio-7B-GGUF
SeaLLMs-Audio-7B-GGUF is a audio-text-to-text model from second-state. Use it for the audio-text-to-text task on the model card, and read the license before you ship it in a product. The card lists the license as other.
<div style="width: auto; margin-left: auto; margin-right: auto" <img src="https://github.com/LlamaEdge/LlamaEdge/raw/dev/assets/logo.svg" style="width: 100%; min-width: 400px; display: block; margin: auto;" </div <hr…
Downloads · 30 days
526
12% of all-time downloads
All-time downloads
4.3K
Public
Repo size
73.9 GB
Likes
1
Public
Click a slice to open those files.
.gguf73.9 GB · 100%
From the Hugging Face model README
| Name | Quant method | Bits | Size | Use case |
|---|---|---|---|---|
| SeaLLMs-Audio-7B-Q2_K.gguf | Q2_K | 2 | 3.03 GB | smallest, significant quality loss - not recommended for most purposes |
| SeaLLMs-Audio-7B-Q3_K_L.gguf | Q3_K_L | 3 | 4.11 GB | small, substantial quality loss |
| SeaLLMs-Audio-7B-Q3_K_M.gguf | Q3_K_M | 3 | 3.83 GB | very small, high quality loss |
| SeaLLMs-Audio-7B-Q3_K_S.gguf | Q3_K_S | 3 | 3.51 GB | very small, high quality loss |
| SeaLLMs-Audio-7B-Q4_0.gguf | Q4_0 | 4 | 4.45 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| SeaLLMs-Audio-7B-Q4_K_M.gguf | Q4_K_M | 4 | 4.70 GB | medium, balanced quality - recommended |
| SeaLLMs-Audio-7B-Q4_K_S.gguf | Q4_K_S | 4 | 4.48 GB | small, greater quality loss |
| SeaLLMs-Audio-7B-Q5_0.gguf | Q5_0 | 5 | 5.34 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| SeaLLMs-Audio-7B-Q5_K_M.gguf | Q5_K_M | 5 | 5.47 GB | large, very low quality loss - recommended |
| SeaLLMs-Audio-7B-Q5_K_S.gguf | Q5_K_S | 5 | 5.34 GB | large, low quality loss - recommended |
| SeaLLMs-Audio-7B-Q6_K.gguf | Q6_K | 6 | 6.28 GB | very large, extremely low quality loss |
| SeaLLMs-Audio-7B-Q8_0.gguf | Q8_0 | 8 | 8.13 GB | very large, extremely low quality loss - not recommended |
| SeaLLMs-Audio-7B-f16.gguf | f16 | 16 | 15.3 GB |
Quantized with llama.cpp b5501