Feedback and support: TensorBlock's Twitter/X, Telegram Group and Discord server
LLM4Binary/llm4decompile-22b-v2 - GGUF
This repo contains GGUF format model files for LLM4Binary/llm4decompile-22b-v2.
The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b4658.
Prompt template
Unable to determine prompt format automatically. Please check the original model repository for the correct prompt format.
Model file specification
| Filename | Quant type | File Size | Description |
|---|---|---|---|
| llm4decompile-22b-v2-Q2_K.gguf | Q2_K | 8.272 GB | smallest, significant quality loss - not recommended for most purposes |
| llm4decompile-22b-v2-Q3_K_S.gguf | Q3_K_S | 9.641 GB | very small, high quality loss |
| llm4decompile-22b-v2-Q3_K_M.gguf | Q3_K_M | 10.757 GB | very small, high quality loss |
| llm4decompile-22b-v2-Q3_K_L.gguf | Q3_K_L | 11.730 GB | small, substantial quality loss |
| llm4decompile-22b-v2-Q4_0.gguf | Q4_0 | 12.569 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| llm4decompile-22b-v2-Q4_K_S.gguf | Q4_K_S | 12.660 GB | small, greater quality loss |
| llm4decompile-22b-v2-Q4_K_M.gguf | Q4_K_M | 13.341 GB | medium, balanced quality - recommended |
| llm4decompile-22b-v2-Q5_0.gguf | Q5_0 | 15.325 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| llm4decompile-22b-v2-Q5_K_S.gguf | Q5_K_S | 15.325 GB | large, low quality loss - recommended |
| llm4decompile-22b-v2-Q5_K_M.gguf | Q5_K_M | 15.723 GB | large, very low quality loss - recommended |
| llm4decompile-22b-v2-Q6_K.gguf | Q6_K | 18.253 GB | very large, extremely low quality loss |
| llm4decompile-22b-v2-Q8_0.gguf | Q8_0 | 23.641 GB | very large, extremely low quality loss - not recommended |
Downloading instruction
Command line
Firstly, install Huggingface Client
pip install -U "huggingface_hub[cli]"
Then, downoad the individual model file the a local directory
huggingface-cli download tensorblock/llm4decompile-22b-v2-GGUF --include "llm4decompile-22b-v2-Q2_K.gguf" --local-dir MY_LOCAL_DIR
If you wanna download multiple model files with a pattern (e.g., *Q4_K*gguf), you can try:
huggingface-cli download tensorblock/llm4decompile-22b-v2-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
- Downloads last month
- 0
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
HF Inference API was unable to determine this model's library.
Model tree for tensorblock/llm4decompile-22b-v2-GGUF
Base model
LLM4Binary/llm4decompile-22b-v2