Feedback and support: TensorBlock's Twitter/X, Telegram Group and Discord server
MaziyarPanahi/Topxtral-4x7B-v0.1 - GGUF
This repo contains GGUF format model files for MaziyarPanahi/Topxtral-4x7B-v0.1.
The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b4011.
Prompt template
Model file specification
| Filename | Quant type | File Size | Description |
|---|---|---|---|
| Topxtral-4x7B-v0.1-Q2_K.gguf | Q2_K | 6.335 GB | smallest, significant quality loss - not recommended for most purposes |
| Topxtral-4x7B-v0.1-Q3_K_S.gguf | Q3_K_S | 7.460 GB | very small, high quality loss |
| Topxtral-4x7B-v0.1-Q3_K_M.gguf | Q3_K_M | 8.283 GB | very small, high quality loss |
| Topxtral-4x7B-v0.1-Q3_K_L.gguf | Q3_K_L | 8.975 GB | small, substantial quality loss |
| Topxtral-4x7B-v0.1-Q4_0.gguf | Q4_0 | 9.734 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| Topxtral-4x7B-v0.1-Q4_K_S.gguf | Q4_K_S | 9.818 GB | small, greater quality loss |
| Topxtral-4x7B-v0.1-Q4_K_M.gguf | Q4_K_M | 10.427 GB | medium, balanced quality - recommended |
| Topxtral-4x7B-v0.1-Q5_0.gguf | Q5_0 | 11.875 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| Topxtral-4x7B-v0.1-Q5_K_S.gguf | Q5_K_S | 11.875 GB | large, low quality loss - recommended |
| Topxtral-4x7B-v0.1-Q5_K_M.gguf | Q5_K_M | 12.232 GB | large, very low quality loss - recommended |
| Topxtral-4x7B-v0.1-Q6_K.gguf | Q6_K | 14.149 GB | very large, extremely low quality loss |
| Topxtral-4x7B-v0.1-Q8_0.gguf | Q8_0 | 18.325 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/Topxtral-4x7B-v0.1-GGUF --include "Topxtral-4x7B-v0.1-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/Topxtral-4x7B-v0.1-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
- Downloads last month
- 193
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.
Model tree for tensorblock/Topxtral-4x7B-v0.1-GGUF
Base model
MaziyarPanahi/Topxtral-4x7B-v0.1