---

license: apache-2.0

library_name: gguf

base_model: King3Djbl/FableForge-1.5B-v2

base_model_relation: quantized

tags:

• gguf
• fableforge
• 1.5b
• llama.cpp
• lm-studio
• ollama
• text-generation
• uncensored
• continued-pretraining
• imatrix
• en

pipeline_tag: text-generation

---

FableForge-1.5B-v2-GGUF

GGUF quantizations of King3Djbl/FableForge-1.5B-v2, a 1.5B parameter model fine-tuned from FableForge-1.5B with continued pretraining for improved reasoning and tool use.

Available Quants

| Quant | File | Size |

|---|---|---|

| F16 | FableForge-1.5B-v2-f16.gguf | 2.88 GB |

| Q8_0 | FableForge-1.5B-v2-q8_0.gguf | 1.53 GB |

| Q6_K | FableForge-1.5B-v2-q6_k.gguf | 1.19 GB |

| Q5_K_M | FableForge-1.5B-v2-q5_k_m.gguf | 1.05 GB |

| Q5_K_S | FableForge-1.5B-v2-q5_k_s.gguf | 1.02 GB |

| Q4_K_M | FableForge-1.5B-v2-q4_k_m.gguf | 0.92 GB |

| Q4_K_S | FableForge-1.5B-v2-q4_k_s.gguf | 0.87 GB |

| Q4_0 | FableForge-1.5B-v2-q4_0.gguf | 0.87 GB |

| Q4_1 | FableForge-1.5B-v2-q4_1.gguf | 0.97 GB |

| Q3_K_L | FableForge-1.5B-v2-q3_k_l.gguf | 0.79 GB |

| Q3_K_M | FableForge-1.5B-v2-q3_k_m.gguf | 0.77 GB |

| Q3_K_S | FableForge-1.5B-v2-q3_k_s.gguf | 0.70 GB |

| Q2_K | FableForge-1.5B-v2-q2_k.gguf | 0.63 GB |

| IQ4_NL | FableForge-1.5B-v2-iq4_nl.gguf | 0.84 GB |

| IQ4_XS | FableForge-1.5B-v2-iq4_xs.gguf | 0.83 GB |

| IQ3_M | FableForge-1.5B-v2-iq3_m.gguf | 0.69 GB |

| IQ3_S | FableForge-1.5B-v2-iq3_s.gguf | 0.65 GB |

| IQ3_XS | FableForge-1.5B-v2-iq3_xs.gguf | 0.62 GB |

| IQ3_XXS | FableForge-1.5B-v2-iq3_xxs.gguf | 0.55 GB |

| IQ2_XS | FableForge-1.5B-v2-iq2_xs.gguf | 0.44 GB |

| IQ2_S | FableForge-1.5B-v2-iq2_s.gguf | 0.48 GB |

| IQ2_XXS | FableForge-1.5B-v2-iq2_xxs.gguf | 0.48 GB |

| IQ1_S | FableForge-1.5B-v2-iq1_s.gguf | 0.41 GB |

Usage

llama.cpp

./main -m FableForge-1.5B-v2-q4_k_m.gguf -p "Hello" -n 512

Ollama

ollama run hf.co/fableforge-ai/FableForge-1.5B-v2-GGUF:Q4_K_M

---

🔗 Related models

• 🧠 V2 base model (safetensors): FableForge-1.5B-v2
• 📊 V1 GGUF: FableForge-1.5B-GGUF