metadata
language:
- code
license: other
model_name: llm-compiler-7b
base_model: facebook/llm-compiler-7b
inference: false
model_creator: facebook
quantized_by: Second State Inc.
llm-compiler-7b-GGUF
Original Model
License A custom commercial license is available at: https://ai.meta.com/resources/models-and-libraries/llama-downloads/
Run with LlamaEdge
- LlamaEdge version: coming soon
Quantized GGUF Models
| Name | Quant method | Bits | Size | Use case |
|---|---|---|---|---|
| llm-compiler-7b-Q2_K.gguf | Q2_K | 2 | 2.53 GB | smallest, significant quality loss - not recommended for most purposes |
| llm-compiler-7b-Q3_K_L.gguf | Q3_K_L | 3 | 3.6 GB | small, substantial quality loss |
| llm-compiler-7b-Q3_K_M.gguf | Q3_K_M | 3 | 3.3 GB | very small, high quality loss |
| llm-compiler-7b-Q3_K_S.gguf | Q3_K_S | 3 | 2.95 GB | very small, high quality loss |
| llm-compiler-7b-Q4_0.gguf | Q4_0 | 4 | 3.83 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| llm-compiler-7b-Q4_K_M.gguf | Q4_K_M | 4 | 4.08 GB | medium, balanced quality - recommended |
| llm-compiler-7b-Q4_K_S.gguf | Q4_K_S | 4 | 3.86 GB | small, greater quality loss |
| llm-compiler-7b-Q5_0.gguf | Q5_0 | 5 | 4.65 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| llm-compiler-7b-Q5_K_M.gguf | Q5_K_M | 5 | 4.78 GB | large, very low quality loss - recommended |
| llm-compiler-7b-Q5_K_S.gguf | Q5_K_S | 5 | 4.65 GB | large, low quality loss - recommended |
| llm-compiler-7b-Q6_K.gguf | Q6_K | 6 | 5.53 GB | very large, extremely low quality loss |
| llm-compiler-7b-Q8_0.gguf | Q8_0 | 8 | 7.16 GB | very large, extremely low quality loss - not recommended |
| llm-compiler-7b-f16.gguf | f16 | f16 | 13.5 GB |
Quantized with llama.cpp b3259