Modelpublic

lucaspetti/ShellWhisperer-1.5B-GGUF

sourceHugging Faceapache-2.0updated 3mo agoView on Hugging Face

0likes144downloads

Model Card

ShellWhisperer-1.5B-GGUF

GGUF quantizations of fableforge-ai/ShellWhisperer-1.5B, a 1.5B parameter instruction-tuned model optimized for shell command generation, agentic tool use, and uncensored reasoning.

Available Quants

Quant	File
F16	`shellwhisperer-1.5b-f16.gguf`
Q8_0	`shellwhisperer-1.5b-Q8_0.gguf`
Q6_K	`shellwhisperer-1.5b-Q6_K.gguf`
Q5KM	`shellwhisperer-1.5b-Q5_K_M.gguf`
Q4KM	`shellwhisperer-1.5b-Q4_K_M.gguf`
Q4_0	`shellwhisperer-1.5b-Q4_0.gguf`
Q3KM	`shellwhisperer-1.5b-Q3_K_M.gguf`
Q2_K	`shellwhisperer-1.5b-Q2_K.gguf`
IQ4_XS	`shellwhisperer-1.5b-IQ4_XS.gguf`
IQ3_XXS	`shellwhisperer-1.5b-IQ3_XXS.gguf`
IQ2_XXS	`shellwhisperer-1.5b-IQ2_XXS.gguf`
IQ1_S	`shellwhisperer-1.5b-IQ1_S.gguf`

Usage

llama.cpp

bash

git clone https://github.com/ggerganov/llama.cpp
cd llama.cpp
make -j
./main -m shellwhisperer-1.5b-Q4_K_M.gguf -p "Generate a bash script to..." -n 512

Ollama

bash

ollama run hf.co/fableforge-ai/ShellWhisperer-1.5B-GGUF:Q4_K_M

LM Studio

Search for "ShellWhisperer" in the LM Studio search panel.