tensorblock/SpecAI-GGUF

Feedback and support: TensorBlock's Twitter/X, Telegram Group and Discord server

gtonkov/SpecAI - GGUF

This repo contains GGUF format model files for gtonkov/SpecAI.

The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b4011.

Run them on the TensorBlock client using your local machine ↗

Prompt template

<s><|system|>
{system_prompt}<|end|>
<|user|>
{prompt}<|end|>
<|assistant|>

Model file specification

Filename	Quant type	File Size	Description
SpecAI-Q2_K.gguf	Q2_K	1.319 GB	smallest, significant quality loss - not recommended for most purposes
SpecAI-Q3_K_S.gguf	Q3_K_S	1.566 GB	very small, high quality loss
SpecAI-Q3_K_M.gguf	Q3_K_M	1.821 GB	very small, high quality loss
SpecAI-Q3_K_L.gguf	Q3_K_L	1.944 GB	small, substantial quality loss
SpecAI-Q4_0.gguf	Q4_0	2.027 GB	legacy; small, very high quality loss - prefer using Q3_K_M
SpecAI-Q4_K_S.gguf	Q4_K_S	2.038 GB	small, greater quality loss
SpecAI-Q4_K_M.gguf	Q4_K_M	2.229 GB	medium, balanced quality - recommended
SpecAI-Q5_0.gguf	Q5_0	2.460 GB	legacy; medium, balanced quality - prefer using Q4_K_M
SpecAI-Q5_K_S.gguf	Q5_K_S	2.460 GB	large, low quality loss - recommended
SpecAI-Q5_K_M.gguf	Q5_K_M	2.622 GB	large, very low quality loss - recommended
SpecAI-Q6_K.gguf	Q6_K	2.920 GB	very large, extremely low quality loss
SpecAI-Q8_0.gguf	Q8_0	3.782 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/SpecAI-GGUF --include "SpecAI-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/SpecAI-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'